{
  "data": {
    "a": {
      "slug": "functionize-mcp",
      "name": "Functionize MCP server",
      "vendor": "Functionize, Inc.",
      "vendorUrl": "https://www.functionize.com",
      "company": "functionize.com",
      "kind": "mcp",
      "category": "browser",
      "summary": "The Functionize MCP server is a hosted remote server from Functionize, Inc. that lets coding agents such as Claude Code, Cursor and GitHub Copilot build, run and diagnose browser tests of a live web app in Functionize Studio.",
      "url": "https://www.anchorterminal.com/tools/functionize-mcp",
      "markdownUrl": "https://www.anchorterminal.com/tools/functionize-mcp.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/functionize-mcp.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/functionize-mcp.json",
      "dns": "functionize-mcp.grade.anchorterminal.com",
      "repo": "https://github.com/FunctionizeInc/functionize-mcp-plugin",
      "license": "Proprietary hosted service under Functionize's Terms of Service (version 2.0, effective 10 July 2026). The Claude Code plugin and its two skills are MIT-licensed; the server's source isn't public",
      "transports": [
        "streamable-http"
      ],
      "remoteUrl": "https://mcp.functionize.com/mcp",
      "packages": [],
      "auth": "oauth",
      "authNotes": "OAuth only, with no API key. The client opens a browser sign-in with the person's Functionize account. The authorisation server metadata gives the authorisation code grant with PKCE S256, refresh tokens, dynamic client registration, client ID metadata documents, public clients only and a revocation endpoint. The protected resource lists the scopes `agent.sessions:read`, `agent.sessions:write` and `offline_access`. The connection works in the account's default team, or the team named in an `X-Functionize-Team-Id` header, checked on every request (403 if not a member). Per SETUP.md it can read, continue or cancel any session in that team, including colleagues' (https://mcp.functionize.com/.well-known/oauth-authorization-server, https://github.com/FunctionizeInc/functionize-mcp-plugin/blob/main/SETUP.md, checked 2026-10-24).",
      "pricing": "freemium",
      "pricingNotes": "Studio's Free plan is $0 with no card and no time limit, with 800,000 credits a month on the plan card (the FAQ on the same page says 400,000) and 5 parallel runs. Growth is $20 a month with 3,200,000 credits and Scale $100 a month with 20,000,000 credits, each with 25 parallel runs, and add-on credits on those two cost $10 per 200,000. Enterprise is custom, with invoice billing and a 12-month minimum. Agent work (creating, running, diagnosing tests) uses credits at a cost that varies by task and isn't published; editing, reports and settings use none. Credits aren't refunded and monthly credits don't roll over. The pricing page has no MCP row; the launch release says the server is available to Studio customers and trial users (https://www.functionize.com/pricing, https://www.functionize.com/usage-limits, checked 2026-11-05).",
      "priceSummary": "$20 / mo",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 on the MCP page, pricing page, usage-limits page, terms or the plugin repository. Unauthenticated MCP calls answer 401 with an OAuth resource-metadata pointer, not a payment request (checked 2026-10-24).",
        "endpoints": []
      },
      "toolCount": 10,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-24"
      },
      "docsUrl": "https://github.com/FunctionizeInc/functionize-mcp-plugin/blob/main/SETUP.md",
      "llmsTxt": "https://www.functionize.com/llms.txt",
      "capabilities": [
        "browser.control",
        "browser.hosted",
        "browser.debug"
      ],
      "tags": [
        "official",
        "hosted",
        "mcp",
        "closed-source",
        "oauth",
        "freemium",
        "no-card",
        "free-tier",
        "status-page",
        "coding-agent",
        "new"
      ],
      "lastRelease": "2026-10-08",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 46.6,
        "grade": "D",
        "agentReady": false,
        "rank": 1246,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 23,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 43,
          "maintenance": 39,
          "payments": 45,
          "reliability": 55,
          "schema": 29,
          "security": 56,
          "transparency": 58
        },
        "assessment": {
          "confidence": "low",
          "date": "2026-11-05"
        },
        "negative": 0,
        "verdict": "Functionize's hosted MCP server hands browser test work to Studio's own agent through ten tools, with OAuth scopes and no API key. Tool definitions sit behind sign-in, the status page has no component for Studio or the server, no rate limits or SLA are published, and a connection can read or cancel colleagues' sessions.",
        "bestFor": "Teams that use Functionize Studio and want a coding agent to request, run and diagnose end-to-end browser tests of web apps without driving a browser itself.",
        "strengths": [
          "OAuth only, with PKCE, dynamic client registration, a revocation endpoint and separate `agent.sessions:read` and `agent.sessions:write` scopes; no API key to leak",
          "A free Studio plan with no card and no time limit, and paid plans from $20 a month published without a login",
          "Ten tools by the README's count, with the long guidance kept in optional Claude Code skills",
          "Failed runs come back with the first failing step, screenshots and logs, and Studio says whether a failure looks like a regression or a page change",
          "SETUP.md covers seven named clients and custom ones with a troubleshooting table and a setup prompt that limits the agent to two configuration changes"
        ],
        "weaknesses": [
          "Tool definitions, input schemas and annotations aren't published; they sit behind OAuth sign-in",
          "No numeric rate limit, 429 guidance or idempotency key was found; only parallel-run limits of 5 or 25 per plan",
          "The status page covers the legacy app hosts, not Studio or mcp.functionize.com",
          "The connection's reach is the whole team, so it can read, continue or cancel colleagues' sessions",
          "Credits per task aren't published, and the Free plan's monthly credits are given as 800,000 and 400,000 on the same page"
        ],
        "agentNotes": [
          "Have the person complete the browser sign-in, which an agent can't do, then check the connection with `list_agent_teams`",
          "Pass the project ID, environment and test ID in `start_agent_session`, and continue a waiting session with `send_agent_message` rather than starting another",
          "Report a created test as done only after a green run, not on a test ID or a green generation",
          "After a dropped connection, list the project's recent tests before creating a test again, since a submitted create finishes on the server",
          "Send the `X-Functionize-Team-Id` header to pin a team, and keep credentials in masked Studio variables, never in prompts"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 2.8,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "low",
            "grade": "D",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 46.6
          }
        ],
        "editorialScores": {
          "ergonomics": 43,
          "maintenance": 39,
          "payments": 45,
          "reliability": 55,
          "schema": 29,
          "security": 56,
          "transparency": 38
        },
        "provenanceScore": 77,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-05",
            "maintenance": "2026-11-05",
            "payments": "2026-11-05",
            "reliability": "2026-11-05",
            "schema": "2026-11-05",
            "security": "2026-11-05",
            "transparency": "2026-11-05"
          },
          "last": "2026-11-05",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-05",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "claude plugin marketplace add FunctionizeInc/functionize-mcp-plugin \u0026\u0026 claude plugin install functionize-mcp@functionize-mcp-plugin",
        "claudeCode": "claude mcp add --transport http functionize https://mcp.functionize.com/mcp",
        "config": {
          "mcpServers": {
            "functionize": {
              "url": "https://mcp.functionize.com/mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/browser.control",
        "tool": "https://letme.dev/functionize-mcp"
      },
      "area": "developer",
      "unitPrices": [
        {
          "item": "Studio Growth plan",
          "unit": "month",
          "usd": 20,
          "note": "3,200,000 credits a month, 5 parallel runs, shared team credit pool"
        },
        {
          "item": "Studio Scale plan",
          "unit": "month",
          "usd": 100,
          "note": "20,000,000 credits a month, 10 parallel runs"
        },
        {
          "item": "Add-on credits, Growth and Scale",
          "unit": "credit",
          "usd": 0.00005,
          "note": "$10 per 200,000 credits; credits per task not published; no refunds or roll-over"
        }
      ],
      "provenance": {
        "legalEntity": "Functionize, Inc.",
        "domain": "functionize.com",
        "domainRegistered": "2015-03-19",
        "endpointOnVendorDomain": true,
        "terms": "https://resources.functionize.com/hubfs/Functionize-ToS.pdf",
        "privacy": "https://www.functionize.com/privacy-policy",
        "statusPage": "https://status.functionize.com/",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-11-05",
        "notes": [
          "The Terms of Service name Functionize, Inc. and California law, version 2.0, effective 10 July 2026, re-read on 2026-11-05. They restrict use of the Service and have no clause on automated access to the website. A 2022 version is still linked in the footer.",
          "The privacy policy is effective 10 July 2026 and supersedes a version of 12 May 2026.",
          "/.well-known/security.txt answered 404 on www.functionize.com on 2026-11-05 (and on mcp.functionize.com on 2026-10-24). The terms give security@functionize.com for credential incidents. trust.functionize.com is behind a Cloudflare Access login and wasn't read.",
          "No changelog was found (/changelog and /release-notes answered 404 on 2026-10-24). Release posts are on the blog.",
          "The status page is incident.io's, re-read from its page and feed. Its components are the legacy app hosts, not Studio or the MCP server.",
          "The registration date is carried from the 24 October record."
        ],
        "score": 77
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/functionize-mcp.json",
      "live": {
        "slug": "functionize-mcp",
        "probe": {
          "target": "https://mcp.functionize.com/mcp",
          "method": "mcp-initialize",
          "lastAt": "2026-11-18T21:56:36.859714779Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 242,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 215,
          "p95ms24h": 344,
          "samples24h": 242,
          "samples30d": 5914,
          "days": [
            {
              "date": "2026-10-25",
              "probes": 102,
              "ok": 102
            },
            {
              "date": "2026-10-26",
              "probes": 252,
              "ok": 252
            },
            {
              "date": "2026-10-27",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-28",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-10-29",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-30",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-10-31",
              "probes": 251,
              "ok": 251
            },
            {
              "date": "2026-11-01",
              "probes": 249,
              "ok": 249
            },
            {
              "date": "2026-11-02",
              "probes": 250,
              "ok": 250
            },
            {
              "date": "2026-11-03",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-11-04",
              "probes": 246,
              "ok": 246
            },
            {
              "date": "2026-11-05",
              "probes": 185,
              "ok": 185
            },
            {
              "date": "2026-11-06",
              "probes": 241,
              "ok": 241
            },
            {
              "date": "2026-11-07",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-08",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-09",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-10",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-11",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-12",
              "probes": 245,
              "ok": 245
            },
            {
              "date": "2026-11-13",
              "probes": 238,
              "ok": 238
            },
            {
              "date": "2026-11-14",
              "probes": 244,
              "ok": 244
            },
            {
              "date": "2026-11-15",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-16",
              "probes": 243,
              "ok": 243
            },
            {
              "date": "2026-11-17",
              "probes": 242,
              "ok": 242
            },
            {
              "date": "2026-11-18",
              "probes": 221,
              "ok": 221
            }
          ],
          "since": "2026-10-25T00:00:00Z"
        },
        "vendorStatus": {
          "page": "https://status.functionize.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-11-18T21:51:11.52461034Z"
        },
        "githubStars": 0,
        "securityTxt": {
          "url": "https://functionize.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-18T16:30:20.920365359Z"
        },
        "llmsTxt": {
          "url": "https://www.functionize.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-11-18T16:14:23.391099539Z"
        },
        "domain": {
          "domain": "functionize.com",
          "registered": "2015-03-19",
          "source": "https://rdap.verisign.com/com/v1/domain/functionize.com",
          "checkedAt": "2026-11-15T15:40:26.639255933Z"
        },
        "pages": [
          {
            "url": "https://www.functionize.com/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-11-17T21:22:41.632579818Z",
            "changedAt": "2026-11-12T17:59:07.659879902Z",
            "fingerprint": "083c436e015b"
          },
          {
            "url": "https://www.functionize.com/privacy-policy",
            "kind": "privacy",
            "status": 200,
            "checkedAt": "2026-11-17T21:22:43.882833008Z",
            "changedAt": "2026-11-04T08:40:20.770373863Z",
            "fingerprint": "39c15213355f"
          }
        ],
        "mcpTools": {
          "url": "https://mcp.functionize.com/mcp",
          "checkedAt": "2026-11-18T04:24:02.080562384Z",
          "status": "auth",
          "note": "asks for credentials before listing its tools",
          "changedAt": "2026-10-26T00:22:49.140266222Z"
        },
        "github": {
          "repo": "functionizeinc/functionize-mcp-plugin",
          "checkedAt": "2026-11-16T11:37:08.885678976Z",
          "stars": 0,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-10-11T13:45:35Z",
          "openIssues": 0,
          "openPRs": 0,
          "issuesOpened90d": 0,
          "issuesClosed90d": 0,
          "prsMerged90d": 0
        },
        "updatedAt": "2026-11-18T21:56:36.859714779Z"
      },
      "streak": {
        "days": 24,
        "from": "2026-10-25",
        "sinceWatching": true,
        "best": 24
      }
    },
    "answer": "Tilion Fortress scores 55.9 (C) on agent readiness against Functionize MCP server's 46.6 (D), and leads in 4 of 7 scored categories. Functionize MCP server leads on reliability and security \u0026 auth.",
    "b": {
      "slug": "tilion-fortress",
      "name": "Tilion Fortress",
      "vendor": "Tilion Inc.",
      "vendorUrl": "https://tilion.dev",
      "company": "tilion.dev",
      "kind": "mcp",
      "category": "browser",
      "summary": "Fortress, from Tilion Inc., is a source-available Chromium fork that alters its fingerprint so automated sessions pass bot detection. It runs locally over CDP, with Python and Node SDKs and a 29-tool stdio MCP server.",
      "url": "https://www.anchorterminal.com/tools/tilion-fortress",
      "markdownUrl": "https://www.anchorterminal.com/tools/tilion-fortress.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tilion-fortress.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tilion-fortress.json",
      "dns": "tilion-fortress.grade.anchorterminal.com",
      "repo": "https://github.com/tiliondev/fortress",
      "license": "Fortress Source Available License 1.1 (not open source). Material released before 30 September 2026 stays under BSD-3-Clause",
      "transports": [
        "stdio"
      ],
      "packages": [
        {
          "registry": "pypi",
          "name": "tilion"
        },
        {
          "registry": "pypi",
          "name": "tilion-fortress"
        },
        {
          "registry": "npm",
          "name": "tilion-mcp"
        },
        {
          "registry": "npm",
          "name": "tilion-fortress"
        }
      ],
      "auth": "none",
      "authNotes": "No credential for the stdio MCP server. The v3 engine needs a free licence key from a sign-in with email, GitHub or Google at tilion.dev/activate (`tilion activate`, or `--headless` for a device code), saved to `~/.tilion/license.jwt` or set as `TILION_LICENSE_KEY` and checked offline. Without a key the public first-generation engine runs.",
      "pricing": "freemium",
      "pricingNotes": "Free for development and testing at any size, and for production by individuals and organisations under US$500,000 in funding and US$300,000 or less in annual recurring revenue. Above that, Enterprise is US$2,000 a month per organisation, billed monthly with a signed production key and Slack support, per fortress.tilion.com/pricing. The repository's subscription terms say three-month terms.",
      "priceSummary": "$2000 / mo",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the repository (checked 2026-11-18). Subscriptions are paid by card, ACH, SEPA, bank transfer or invoice at checkout.",
        "endpoints": []
      },
      "toolCount": 29,
      "popularity": {
        "githubStars": 804,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://github.com/tiliondev/fortress#readme",
      "llmsTxt": "https://raw.githubusercontent.com/tiliondev/fortress/main/llms.txt",
      "registryName": "io.github.tiliondev/fortress",
      "capabilities": [
        "browser.control",
        "scraping.anti-bot",
        "scraping.js-render",
        "web.extract",
        "web.crawl",
        "web.search"
      ],
      "tags": [
        "local",
        "self-hosted",
        "source-available",
        "mcp",
        "cli",
        "docker",
        "python",
        "typescript",
        "browser",
        "headless",
        "stealth",
        "mcp-registry",
        "llms-txt",
        "agent-skills",
        "no-card",
        "freemium",
        "beta",
        "new"
      ],
      "lastRelease": "2026-10-05",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 55.9,
        "grade": "C",
        "agentReady": false,
        "rank": 967,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 21,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 73,
          "maintenance": 47,
          "payments": 60,
          "reliability": 46,
          "schema": 74,
          "security": 35,
          "transparency": 58
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "warnings": [
          {
            "kind": "operator-unidentified",
            "name": "Operator not identified",
            "text": "Fortress's licence and subscription terms name Tilion Inc., and tilion.com's terms name no company, only Delaware law, with no state of registration, registration number or address. OpenCorporates refused our reader (403), SEC EDGAR's search is closed to it by robots.txt, and Delaware's entity search needs a form it can't submit, so no register entry was found.",
            "deduct": 0,
            "capGrade": "B",
            "since": "2026-11-18",
            "sources": [
              "https://tilion.com/terms",
              "https://tilion.com/privacy",
              "https://fortress.tilion.com/pricing",
              "https://github.com/tiliondev/fortress"
            ]
          }
        ],
        "verdict": "Fortress gives agents 29 annotated MCP tools on a local stealth Chromium, with an SSRF guard, capped output and statuses that name the blocking vendor. Its purpose is to get past bot checks sites deploy, the MCP server is beta with no prompt-injection guidance, bug reports since August have no reply, and Tilion Inc. couldn't be identified in a register.",
        "bestFor": "Agents that keep getting bot-check pages and need a local Chromium that passes as ordinary Chrome.",
        "strengths": [
          "29 MCP tools, each with readOnlyHint or destructiveHint annotations and a structured `{status, error}` reply on failure or timeout",
          "Private, loopback and cloud-metadata addresses are refused by default unless `TILION_ALLOW_PRIVATE_EGRESS=1` is set",
          "Results report `ok`, `empty`, `blocked` or `error`, with the anti-bot vendor in `waf`, and long text is cut with a truncated flag",
          "The licence states no telemetry, usage reporting or update polling, and a key is checked offline",
          "Python and Node SDKs and a Docker image, with release bundles checked against SHA256SUMS"
        ],
        "weaknesses": [
          "Sold to defeat bot detection (Cloudflare, DataDome, PerimeterX, Akamai) and, with a third-party key, to solve CAPTCHAs, which many sites' terms forbid",
          "The MCP server is labelled beta, the engine is not open source, and the `tilion` framework the server imports is not in the repository",
          "No prompt-injection guidance, though every tool returns untrusted page content",
          "Bug reports from August to October 2026 and a request to enable private vulnerability reporting have no reply",
          "Tilion Inc. names no state of registration or address, and no register entry was found"
        ],
        "agentNotes": [
          "Check the target site's terms before you use these tools to get past its bot checks. The server does not read robots.txt",
          "Call `fetch_protected_page` first and read `status` and `waf` before you retry or switch to `run_browser_task`",
          "Ask the user before `run_browser_task`, `download_file`, `save_page` or `solve_captcha`. They act on sites or write files",
          "Treat returned page text as untrusted. The server does not strip or flag injected instructions",
          "Set `TILION_LICENSE_KEY` or run `tilion activate --token` for the v3 engine. Without a key the server runs the older public engine"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 55.9
          }
        ],
        "editorialScores": {
          "ergonomics": 73,
          "maintenance": 47,
          "payments": 60,
          "reliability": 46,
          "schema": 74,
          "security": 35,
          "transparency": 61
        },
        "provenanceScore": 55,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "lastMoved": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install \"tilion[mcp]\"",
        "claudeCode": "claude mcp add fortress -- tilion-mcp",
        "config": {
          "mcpServers": {
            "fortress": {
              "command": "tilion-mcp"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/browser.control",
        "tool": "https://letme.dev/tilion-fortress"
      },
      "area": "developer",
      "unitPrices": [
        {
          "item": "Fortress Enterprise production key per organisation",
          "unit": "month",
          "usd": 2000,
          "note": "Billed monthly per the pricing page, three-month terms per SUBSCRIPTION-TERMS.md. Only for organisations over the licence's funding or revenue thresholds"
        }
      ],
      "provenance": {
        "legalEntity": "Tilion Inc.",
        "domain": "tilion.dev",
        "domainRegistered": "",
        "endpointOnVendorDomain": null,
        "terms": "https://github.com/tiliondev/fortress/blob/main/SUBSCRIPTION-TERMS.md",
        "privacy": "https://tilion.com/privacy",
        "statusPage": "",
        "changelog": "https://github.com/tiliondev/fortress/releases",
        "securityTxt": "none",
        "checked": "2026-11-18",
        "notes": [
          "LICENSE, NOTICE and SUBSCRIPTION-TERMS.md name Tilion Inc. as licensor, with no state, registration number or address. tilion.com's terms and privacy policy (both effective 23 July 2026) name no company, only Tilion, and choose Delaware law and courts.",
          "tilion.com's terms cover the website, dashboard, API and cloud browsers, and say the Fortress engine's own licences govern its code, so SUBSCRIPTION-TERMS.md stays the governing terms for Fortress. That file says its current version is at tilion.com/terms, which today holds only the cloud terms. The privacy policy covers tilion.com, the dashboard and the API, where the v3 key is issued.",
          "tilion.dev answers robots.txt with no rules and redirects to tilion.com, whose robots.txt disallows only sign-in, dashboard and API paths. tilion.com answers 404 for /.well-known/security.txt (read 18 November 2026).",
          "SECURITY.md routes reports to GitHub private vulnerability reporting, but an open issue of 20 August 2026 titled \"Enable private vulnerability reporting\" has no reply."
        ],
        "score": 55
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/tilion-fortress.json"
    },
    "edges": [
      {
        "by": 45,
        "category": "schema",
        "leads": "tilion-fortress",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "No machine-readable contract could be read. The tools sit behind OAuth sign-in and no public tool manifest, server card or source was found, so typed inputs on the tools are unchecked (0 of 25). llms.txt is an August 2025 crawl of the marketing site with no mention of MCP, but SETUP.md is Markdown written for an agent to run and the two skills are Markdown references for agents (10). Purpose and when to use each tool come only from the skills, which describe the session loop and say what Studio can't do; the tool descriptions themselves weren't read (8 of 20). Typed inputs, enums and constraints unread (0 of 15). Example prompts in the release posts and skills, and a troubleshooting table in SETUP.md with the 403 on a wrong team, `redirect_uri not permitted` and the unknown-tool reply; no documented error shape for tool calls (8 of 15). The plugin is versioned (1.1.0, skills 2.12.0 and 2.40.0) with a dated git history, but the server has no version or changelog (3 of 15). 0 + 10 + 8 + 0 + 8 + 3 = 29.",
          "b": "Read from mcp/server.py, mcp/README.md and mcp/USAGE.md in the repository. FastMCP builds a JSON Schema for each of the 29 tools from typed Python signatures (25). llms.txt and an AGENTS.md setup guide in the repository, and an agent skill in mcp/skill (10). Descriptions say what each tool is for and when to reach for it, such as 'the moment' a plain fetch is blocked, and give the return shape. Few say when not to use a tool (14). Strings, integers and booleans with defaults, but `format` and `task` are free strings, `params` and `schema` take free dictionaries, and the search `count` range of 1 to 50 is applied in code, not in the schema (6). USAGE.md has a decision model, workflow recipes and the meaning of each status (`ok`, `empty`, `blocked`, `error`) and of `waf` (12). Release tags with notes for the engine, a version in server.json, no changelog for the MCP tools (7). 25 + 10 + 14 + 6 + 12 + 7 = 74."
        },
        "scores": {
          "a": 29,
          "b": 74
        }
      },
      {
        "by": 30,
        "category": "ergonomics",
        "leads": "tilion-fortress",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Graded on the MCP server. 10 tools by the README's count, with the long guidance moved into Claude Code skills that load only when used. The size of the definitions couldn't be read, so 20 of 25 rather than 25 for compact tools. Sessions can be listed and their events read or streamed, but no page size, filter or output-size control was found (5 of 20). Results carry the failing step, screenshots and logs, and SETUP.md maps symptoms to fixes; no error codes for tool calls were found (8 of 20). No idempotency key, and readOnlyHint and destructiveHint couldn't be checked; the skill's advice to list recent tests before creating again is the only retry guidance (3 of 20). Requests are plain words, the team defaults to the account's own and sign-in needs no key, but there's no official SDK (7 of 15). 20 + 5 + 8 + 3 + 7 = 43.",
          "b": "29 tools, about 7,200 characters of descriptions, with no toolsets or read-only subset (15). Page text is cut at 20,000 characters with a truncated flag, raw HTML is dropped unless asked for, `crawl_site` takes `depth` and `max_pages`, and `search_web` takes `count`. No pagination (14). Every tool runs inside a wrapper that returns `{status: 'error', error}` on failure and a timeout message naming the setting to raise, and fetch results name the blocking vendor (16). Every tool carries readOnlyHint or destructiveHint. No idempotency guidance (15). Most tools need only `url`. Python and Node SDKs for the engine (13). 15 + 14 + 16 + 15 + 13 = 73."
        },
        "scores": {
          "a": 43,
          "b": 73
        }
      },
      {
        "by": 21,
        "category": "security",
        "leads": "functionize-mcp",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "OAuth only. The metadata gives the authorisation code grant with PKCE S256, refresh tokens, dynamic client registration, client ID metadata documents, public clients and a revocation endpoint, with scopes `agent.sessions:read`, `agent.sessions:write` and `offline_access`. No API key exists and tokens go in the header only (30). The connection's reach is the whole team. Per SETUP.md it can read, continue or cancel any session in the team, including colleagues', and delete attachments on one. No documented way to request the read scope alone, and no approval step for writes, though the server has no file-system access and Functionize says Studio doesn't decide releases (8 of 20). Results include text and screenshots from the app under test, which is the customer's own but untrusted. No guidance on that was found; SETUP.md's setup prompt confines the agent to two configuration changes and tells it to stop if asked for more, and the skills keep credentials in masked variables (5 of 15). Sessions and run history with screenshots and logs are visible in Studio, and usage in the sidebar and reports; an audit-logs row is commented out of the pricing page (7 of 15). No security.txt (404 on www.functionize.com on 5 November), no bug bounty or advisories found, security@functionize.com named in the terms, SOC 2 Type II adherence claimed in the privacy policy with no report public, and trust.functionize.com behind a login (6 of 20). The OAuth metadata is the published discovery documents read on 24 October, not re-read on 5 November. 30 + 8 + 5 + 7 + 6 = 56.",
          "b": "Read as local software. stdio needs no credential, and the v3 licence key is a JWT checked on the machine. A hosted mode with `TILION_API_KEY` is described as coming soon (18). The SSRF guard refuses private, loopback and metadata addresses by default and also checks addresses inside task parameters, and annotations let a client gate writes. `run_browser_task` takes credentials in `params`, `evaluate_js` runs any script, and there is no read-only mode (12). Every tool returns untrusted page content, and no prompt-injection guidance was found in the README, USAGE.md, AGENTS.md or llms.txt (0). No call log or audit trail found (0). SECURITY.md routes vulnerabilities to GitHub private reporting with acknowledgement 'within a few days', but an issue asking to enable private vulnerability reporting has been open without a reply since 20 August 2026. Fixes go to the latest release only, and releases carry SHA256SUMS. No bounty, security.txt or advisories found (5). 18 + 12 + 0 + 0 + 5 = 35."
        },
        "scores": {
          "a": 56,
          "b": 35
        }
      },
      {
        "by": 15,
        "category": "payments",
        "leads": "tilion-fortress",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No x402, MPP or L402 (0). Plan prices are public ($0, $20 and $100 a month with their credits, add-on credits at $10 per 200,000), re-read on 5 November, but the credits a task uses aren't published, so plan-only pricing (10). A Free plan with no card and no time limit (20). A person has to sign up for Studio and sign in through a browser before any call works (0). 0 + 10 + 20 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.",
          "b": "Read with the rule for self-hosted software with a paid option. No payment protocol (0). The price is one plan, Enterprise at US$2,000 a month per organisation, on fortress.tilion.com/pricing, with a free Developer tier (15). Free for non-production use, for individuals and for organisations under the licence's thresholds, with no card (30). The v3 key needs a person to sign in with email, GitHub or Google at tilion.dev/activate, though `--headless` prints a code for another device. Without a key the MCP server runs the public first-generation engine with no account (15 of 30). 0 + 15 + 30 + 15 = 60."
        },
        "scores": {
          "a": 45,
          "b": 60
        }
      },
      {
        "by": 9,
        "category": "reliability",
        "leads": "functionize-mcp",
        "name": "Reliability",
        "reasons": {
          "a": "Graded with the hosted lines, on the remote MCP server. Functionize has a status page at status.functionize.com (incident.io) with incident history, re-read from the page and its feed on 5 November, but its components are app.functionize.com and two virtualautomationengineer.com hosts, not Studio or mcp.functionize.com. A vendor status page with no component for the product takes 15, as for sourcegraph-mcp. In the 90 days from 7 August it records one incident, slower test creation and execution on 22 October on app.functionize.com, read as minor (20). No request rate limit is published with numbers; the only limits are 5 or 25 parallel runs and monthly credits per plan (5 of 15, held). No 429 or Retry-After guidance was found. The plugin's skill says a create submitted before a dropped connection finishes on the server and to list recent tests before creating again, which is safe-retry guidance of a kind (5 of 15, held). The terms say self-service plans have no SLA and service levels apply only where an Order Form states them, with no figure published (0). The release of 8 October calls the server available today and nothing labels it beta (10). 15 + 20 + 5 + 5 + 0 + 10 = 55.",
          "b": "Read on the local-software lines, since the engine and the MCP server run on the user's machine. Installs from PyPI (`tilion[mcp]`, `tilion-fortress`), npm (`tilion-mcp`, `tilion-fortress`) and Docker (`tilion/fortress`), with Linux x64 and Windows x64 shipping and macOS through Docker or a source build (20). ci.yml lints the 81-patch series and runs the Python SDK tests on 3.9 and 3.12 and the Node SDK tests on every push. Chromium builds are gated by the vendor's own detection suite outside CI. No CI tests for the MCP server, and run results couldn't be read (12 of 25). Seven issues were open on 18 November 2026. Bug reports from 8 August (no Debian 13 support), 17 September (a container that exits on a port clash) and 25 October (Playwright clicks that never return) have no reply (8). Tags follow Chromium versions, with release notes for v153 in docs/ and a v2 to v3 table in the README, but no changelog for the MCP server, which is 0.1.3 in server.json and 0.1.0 in the npm package (6 of 15). The MCP server is labelled beta (0). 20 + 12 + 8 + 6 + 0 = 46."
        },
        "scores": {
          "a": 55,
          "b": 46
        }
      },
      {
        "by": 8,
        "category": "maintenance",
        "leads": "tilion-fortress",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Read as a closed hosted service with a public plugin repository. The server was released on 8 October 2026, 28 days before this check, and nothing newer is dated (30). In the 90 days from 7 August the only dated release is that launch; the plugin repository has commits from 26 August to 10 October 2026 and an untagged bump to 1.1.0 on 16 September, which isn't a release, and no changelog, so fewer than three (0). Support is through the in-app system with published response goals (2 hours for critical and high, 4 for medium, 24 for low), stated as goals, not commitments. No public changelog or community channel, and issue replies weren't read (6 of 25, held). No readable official MCP registry page names it and there's no official SDK (0). The plugin is MIT with a current manifest but no CI or tests (3 of 10). 30 + 0 + 6 + 0 + 3 = 39.",
          "b": "Last tag v156.0.8078.47 and last commit on 5 October 2026, 44 days before 18 November. PyPI and npm versions couldn't be read (20). Two tags in the 90 days, v153.0.8010.36 on 30 September and v156 on 5 October (0). Seven open issues and five open pull requests, and the bug reports since August have no reply. There is a Discord and a contributing guide (5 of 25). The official MCP registry lists `io.github.tiliondev/fortress` 0.1.3 as active, published 7 July 2026 (15). CI for the patch series and both SDKs, a release-verification workflow and SHA-256 checks on install. Run results unread (7 of 10). 20 + 0 + 5 + 15 + 7 = 47."
        },
        "scores": {
          "a": 39,
          "b": 47
        }
      }
    ],
    "facts": [
      {
        "a": "MCP server",
        "b": "MCP server",
        "name": "Kind"
      },
      {
        "a": "Functionize, Inc.",
        "b": "Tilion Inc.",
        "name": "Vendor"
      },
      {
        "a": "https://mcp.functionize.com/mcp",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "Streamable HTTP",
        "b": "stdio",
        "name": "Transports"
      },
      {
        "a": "OAuth",
        "b": "None",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Proprietary hosted service under Functionize's Terms of Service (version 2.0, effective 10 July 2026). The Claude Code plugin and its two skills are MIT-licensed; the server's source isn't public",
        "b": "Fortress Source Available License 1.1 (not open source). Material released before 30 September 2026 stays under BSD-3-Clause",
        "name": "Licence"
      },
      {
        "a": "10",
        "b": "29",
        "name": "Tools exposed"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "not listed",
        "b": "io.github.tiliondev/fortress",
        "name": "MCP registry"
      },
      {
        "a": "2026-10-08",
        "b": "2026-10-05",
        "name": "Last release"
      },
      {
        "a": "not read yet",
        "b": "no date given",
        "name": "Terms last updated"
      },
      {
        "a": "2026-07-10",
        "b": "2026-07-23",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not read yet",
        "b": "not found in the text",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "none",
        "b": "804 stars",
        "name": "Popularity"
      },
      {
        "a": "2.8/5 (4)",
        "b": "none",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Tilion Fortress scores 55.9 (C) on agent readiness against Functionize MCP server's 46.6 (D), and leads in 4 of 7 scored categories. Functionize MCP server leads on reliability and security \u0026 auth.",
        "question": "Which is better for AI agents, Functionize MCP server or Tilion Fortress?"
      },
      {
        "answer": "Functionize MCP server uses an OAuth sign-in. Tilion Fortress needs no key.",
        "question": "Do Functionize MCP server and Tilion Fortress need an API key?"
      },
      {
        "answer": "Functionize MCP server has a hosted endpoint at https://mcp.functionize.com/mcp. Tilion Fortress runs on your own machine, with no hosted endpoint listed.",
        "question": "Can an agent call Functionize MCP server and Tilion Fortress without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 55 against 46",
          "Security \u0026 auth, 56 against 35"
        ],
        "also": [
          "A hosted endpoint, with nothing to install"
        ],
        "goodFor": "Teams that use Functionize Studio and want a coding agent to request, run and diagnose end-to-end browser tests of web apps without driving a browser itself.",
        "slug": "functionize-mcp",
        "watchFor": "Tool definitions, input schemas and annotations aren't published; they sit behind OAuth sign-in"
      },
      {
        "aheadOn": [
          "Schema \u0026 documentation, 74 against 29",
          "Agent ergonomics, 73 against 43",
          "Payments \u0026 pricing, 60 against 45",
          "Maintenance \u0026 community, 47 against 39"
        ],
        "also": [
          "No key needed to call it",
          "Runs on your own machine"
        ],
        "goodFor": "Agents that keep getting bot-check pages and need a local Chromium that passes as ordinary Chrome.",
        "slug": "tilion-fortress",
        "watchFor": "Sold to defeat bot detection (Cloudflare, DataDome, PerimeterX, Akamai) and, with a third-party key, to solve CAPTCHAs, which many sites' terms forbid"
      }
    ],
    "history": {
      "functionize-mcp": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 1.9,
          "from": 44.7,
          "fromGrade": "E",
          "to": 46.6,
          "toGrade": "D"
        },
        {
          "causes": [
            "correction"
          ],
          "date": "2026-11-05",
          "delta": 0.1,
          "from": 44.6,
          "fromGrade": "E",
          "to": 44.7,
          "toGrade": "E"
        },
        {
          "causes": [
            "method"
          ],
          "date": "2026-10-30",
          "delta": -0.3,
          "from": 44.9,
          "fromGrade": "E",
          "to": 44.6,
          "toGrade": "E"
        }
      ],
      "tilion-fortress": [
        {
          "causes": [
            "terms",
            "security",
            "evidence"
          ],
          "date": "2026-11-18",
          "delta": 1.9,
          "from": 54,
          "fromGrade": "C",
          "to": 55.9,
          "toGrade": "C"
        }
      ]
    },
    "job": {
      "capability": "browser.control",
      "name": "Browser automation"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent-browser-vs-functionize-mcp.json",
        "title": "agent-browser vs Functionize MCP server",
        "url": "https://www.anchorterminal.com/compare/agent-browser-vs-functionize-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent-browser-vs-tilion-fortress.json",
        "title": "agent-browser vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/agent-browser-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/airtop-vs-functionize-mcp.json",
        "title": "Airtop vs Functionize MCP server",
        "url": "https://www.anchorterminal.com/compare/airtop-vs-functionize-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/airtop-vs-tilion-fortress.json",
        "title": "Airtop vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/airtop-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-functionize-mcp.json",
        "title": "Anchor Browser vs Functionize MCP server",
        "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-functionize-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-tilion-fortress.json",
        "title": "Anchor Browser vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.json",
        "title": "AutoCua vs Functionize MCP server",
        "url": "https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/autocua-vs-tilion-fortress.json",
        "title": "AutoCua vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/autocua-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browser-use-vs-functionize-mcp.json",
        "title": "Browser Use vs Functionize MCP server",
        "url": "https://www.anchorterminal.com/compare/browser-use-vs-functionize-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browser-use-vs-tilion-fortress.json",
        "title": "Browser Use vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/browser-use-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browserbase-vs-tilion-fortress.json",
        "title": "Browserbase vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/browserbase-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browserless-vs-functionize-mcp.json",
        "title": "Browserless vs Functionize MCP server",
        "url": "https://www.anchorterminal.com/compare/browserless-vs-functionize-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browserless-vs-tilion-fortress.json",
        "title": "Browserless vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/browserless-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bx-playwright-vs-functionize-mcp.json",
        "title": "BxPlaywright vs Functionize MCP server",
        "url": "https://www.anchorterminal.com/compare/bx-playwright-vs-functionize-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/bx-playwright-vs-tilion-fortress.json",
        "title": "BxPlaywright vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/bx-playwright-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-functionize-mcp.json",
        "title": "Chrome DevTools MCP vs Functionize MCP server",
        "url": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-functionize-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-tilion-fortress.json",
        "title": "Chrome DevTools MCP vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-hyperbrowser.json",
        "title": "Functionize MCP server vs Hyperbrowser",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-hyperbrowser"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-kane-cli.json",
        "title": "Functionize MCP server vs Kane CLI",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-kane-cli"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-kernel.json",
        "title": "Functionize MCP server vs Kernel",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-kernel"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-lightpanda.json",
        "title": "Functionize MCP server vs Lightpanda",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-lightpanda"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-notte.json",
        "title": "Functionize MCP server vs Notte",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-notte"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-playwright-mcp.json",
        "title": "Functionize MCP server vs Playwright MCP",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-playwright-mcp"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-pomerado.json",
        "title": "Functionize MCP server vs Pomerado",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-pomerado"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer.json",
        "title": "Functionize MCP server vs Puppeteer",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer-reference-server-archived.json",
        "title": "Functionize MCP server vs Puppeteer (archived MCP reference server)",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer-reference-server-archived"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-selenium.json",
        "title": "Functionize MCP server vs Selenium",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-selenium"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-skyvern.json",
        "title": "Functionize MCP server vs Skyvern",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-skyvern"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-steel.json",
        "title": "Functionize MCP server vs Steel",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-steel"
      },
      {
        "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-tinyfish.json",
        "title": "Functionize MCP server vs TinyFish",
        "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-tinyfish"
      },
      {
        "json": "https://www.anchorterminal.com/compare/hyperbrowser-vs-tilion-fortress.json",
        "title": "Hyperbrowser vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/hyperbrowser-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/kane-cli-vs-tilion-fortress.json",
        "title": "Kane CLI vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/kane-cli-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/kernel-vs-tilion-fortress.json",
        "title": "Kernel vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/kernel-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/lightpanda-vs-tilion-fortress.json",
        "title": "Lightpanda vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/lightpanda-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/notte-vs-tilion-fortress.json",
        "title": "Notte vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/notte-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/playwright-mcp-vs-tilion-fortress.json",
        "title": "Playwright MCP vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/playwright-mcp-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/pomerado-vs-tilion-fortress.json",
        "title": "Pomerado vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/pomerado-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-tilion-fortress.json",
        "title": "Puppeteer (archived MCP reference server) vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/puppeteer-vs-tilion-fortress.json",
        "title": "Puppeteer vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/puppeteer-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/selenium-vs-tilion-fortress.json",
        "title": "Selenium vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/selenium-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/skyvern-vs-tilion-fortress.json",
        "title": "Skyvern vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/skyvern-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/steel-vs-tilion-fortress.json",
        "title": "Steel vs Tilion Fortress",
        "url": "https://www.anchorterminal.com/compare/steel-vs-tilion-fortress"
      },
      {
        "json": "https://www.anchorterminal.com/compare/tilion-fortress-vs-tinyfish.json",
        "title": "Tilion Fortress vs TinyFish",
        "url": "https://www.anchorterminal.com/compare/tilion-fortress-vs-tinyfish"
      },
      {
        "json": "https://www.anchorterminal.com/compare/browserbase-vs-functionize-mcp.json",
        "title": "Browserbase vs Functionize MCP server",
        "url": "https://www.anchorterminal.com/compare/browserbase-vs-functionize-mcp"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 9,
        "edge": "functionize-mcp",
        "functionize-mcp": 55,
        "key": "reliability",
        "name": "Reliability",
        "tilion-fortress": 46,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 45,
        "edge": "tilion-fortress",
        "functionize-mcp": 29,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "tilion-fortress": 74,
        "weight": 13
      },
      {
        "by": 30,
        "edge": "tilion-fortress",
        "functionize-mcp": 43,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "tilion-fortress": 73,
        "weight": 13
      },
      {
        "by": 21,
        "edge": "functionize-mcp",
        "functionize-mcp": 56,
        "key": "security",
        "name": "Security \u0026 auth",
        "tilion-fortress": 35,
        "weight": 14
      },
      {
        "by": 15,
        "edge": "tilion-fortress",
        "functionize-mcp": 45,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "tilion-fortress": 60,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 8,
        "edge": "tilion-fortress",
        "functionize-mcp": 39,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "tilion-fortress": 47,
        "weight": 7
      },
      {
        "by": 0,
        "edge": "",
        "functionize-mcp": 58,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "tilion-fortress": 58,
        "weight": 7
      }
    ],
    "summary": "Tilion Fortress scores 55.9 (C) on agent readiness against Functionize MCP server's 46.6 (D), and leads in 4 of 7 scored categories. Functionize MCP server leads on reliability and security \u0026 auth. Both do browser automation.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "functionize-mcp": "Functionize's hosted MCP server hands browser test work to Studio's own agent through ten tools, with OAuth scopes and no API key. Tool definitions sit behind sign-in, the status page has no component for Studio or the server, no rate limits or SLA are published, and a connection can read or cancel colleagues' sessions.",
      "tilion-fortress": "Fortress gives agents 29 annotated MCP tools on a local stealth Chromium, with an SSRF guard, capped output and statuses that name the blocking vendor. Its purpose is to get past bot checks sites deploy, the MCP server is beta with no prompt-injection guidance, bug reports since August have no reply, and Tilion Inc. couldn't be identified in a register."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/functionize-mcp-vs-tilion-fortress",
    "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-tilion-fortress.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/functionize-mcp-vs-tilion-fortress.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/functionize-mcp-vs-tilion-fortress.min.md"
  },
  "markdown": "Tilion Fortress scores 55.9 (C) on agent readiness against Functionize MCP server's 46.6 (D), and leads in 4 of 7 scored categories. Functionize MCP server leads on reliability and security \u0026 auth. Both do browser automation.\n\n- Functionize MCP server: grade D, 46.6/100, rank #1246 of 1557. Markdown https://www.anchorterminal.com/tools/functionize-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/functionize-mcp.json\n- Tilion Fortress: grade C, 55.9/100, rank #967 of 1557. Markdown https://www.anchorterminal.com/tools/tilion-fortress.md · JSON https://www.anchorterminal.com/api/v1/tools/tilion-fortress.json\n- Best browser automation tools for AI agents: https://www.anchorterminal.com/best/browser/index.md\n- All 308 browser comparisons: https://www.anchorterminal.com/compare/browser/index.md\n\n## Which one, for what\n\n### Functionize MCP server (D)\n\nGood for: Teams that use Functionize Studio and want a coding agent to request, run and diagnose end-to-end browser tests of web apps without driving a browser itself.\n\nAhead on:\n- Reliability, 55 against 46\n- Security \u0026 auth, 56 against 35\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: Tool definitions, input schemas and annotations aren't published; they sit behind OAuth sign-in\n\n### Tilion Fortress (C)\n\nGood for: Agents that keep getting bot-check pages and need a local Chromium that passes as ordinary Chrome.\n\nAhead on:\n- Schema \u0026 documentation, 74 against 29\n- Agent ergonomics, 73 against 43\n- Payments \u0026 pricing, 60 against 45\n- Maintenance \u0026 community, 47 against 39\n\nAlso in its favour:\n- No key needed to call it\n- Runs on your own machine\n\nWatch for: Sold to defeat bot detection (Cloudflare, DataDome, PerimeterX, Akamai) and, with a third-party key, to solve CAPTCHAs, which many sites' terms forbid\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Tilion Fortress +45\n\n- Functionize MCP server (29): No machine-readable contract could be read. The tools sit behind OAuth sign-in and no public tool manifest, server card or source was found, so typed inputs on the tools are unchecked (0 of 25). llms.txt is an August 2025 crawl of the marketing site with no mention of MCP, but SETUP.md is Markdown written for an agent to run and the two skills are Markdown references for agents (10). Purpose and when to use each tool come only from the skills, which describe the session loop and say what Studio can't do; the tool descriptions themselves weren't read (8 of 20). Typed inputs, enums and constraints unread (0 of 15). Example prompts in the release posts and skills, and a troubleshooting table in SETUP.md with the 403 on a wrong team, `redirect_uri not permitted` and the unknown-tool reply; no documented error shape for tool calls (8 of 15). The plugin is versioned (1.1.0, skills 2.12.0 and 2.40.0) with a dated git history, but the server has no version or changelog (3 of 15). 0 + 10 + 8 + 0 + 8 + 3 = 29.\n- Tilion Fortress (74): Read from mcp/server.py, mcp/README.md and mcp/USAGE.md in the repository. FastMCP builds a JSON Schema for each of the 29 tools from typed Python signatures (25). llms.txt and an AGENTS.md setup guide in the repository, and an agent skill in mcp/skill (10). Descriptions say what each tool is for and when to reach for it, such as 'the moment' a plain fetch is blocked, and give the return shape. Few say when not to use a tool (14). Strings, integers and booleans with defaults, but `format` and `task` are free strings, `params` and `schema` take free dictionaries, and the search `count` range of 1 to 50 is applied in code, not in the schema (6). USAGE.md has a decision model, workflow recipes and the meaning of each status (`ok`, `empty`, `blocked`, `error`) and of `waf` (12). Release tags with notes for the engine, a version in server.json, no changelog for the MCP tools (7). 25 + 10 + 14 + 6 + 12 + 7 = 74.\n\n### Agent ergonomics: Tilion Fortress +30\n\n- Functionize MCP server (43): Graded on the MCP server. 10 tools by the README's count, with the long guidance moved into Claude Code skills that load only when used. The size of the definitions couldn't be read, so 20 of 25 rather than 25 for compact tools. Sessions can be listed and their events read or streamed, but no page size, filter or output-size control was found (5 of 20). Results carry the failing step, screenshots and logs, and SETUP.md maps symptoms to fixes; no error codes for tool calls were found (8 of 20). No idempotency key, and readOnlyHint and destructiveHint couldn't be checked; the skill's advice to list recent tests before creating again is the only retry guidance (3 of 20). Requests are plain words, the team defaults to the account's own and sign-in needs no key, but there's no official SDK (7 of 15). 20 + 5 + 8 + 3 + 7 = 43.\n- Tilion Fortress (73): 29 tools, about 7,200 characters of descriptions, with no toolsets or read-only subset (15). Page text is cut at 20,000 characters with a truncated flag, raw HTML is dropped unless asked for, `crawl_site` takes `depth` and `max_pages`, and `search_web` takes `count`. No pagination (14). Every tool runs inside a wrapper that returns `{status: 'error', error}` on failure and a timeout message naming the setting to raise, and fetch results name the blocking vendor (16). Every tool carries readOnlyHint or destructiveHint. No idempotency guidance (15). Most tools need only `url`. Python and Node SDKs for the engine (13). 15 + 14 + 16 + 15 + 13 = 73.\n\n### Security \u0026 auth: Functionize MCP server +21\n\n- Functionize MCP server (56): OAuth only. The metadata gives the authorisation code grant with PKCE S256, refresh tokens, dynamic client registration, client ID metadata documents, public clients and a revocation endpoint, with scopes `agent.sessions:read`, `agent.sessions:write` and `offline_access`. No API key exists and tokens go in the header only (30). The connection's reach is the whole team. Per SETUP.md it can read, continue or cancel any session in the team, including colleagues', and delete attachments on one. No documented way to request the read scope alone, and no approval step for writes, though the server has no file-system access and Functionize says Studio doesn't decide releases (8 of 20). Results include text and screenshots from the app under test, which is the customer's own but untrusted. No guidance on that was found; SETUP.md's setup prompt confines the agent to two configuration changes and tells it to stop if asked for more, and the skills keep credentials in masked variables (5 of 15). Sessions and run history with screenshots and logs are visible in Studio, and usage in the sidebar and reports; an audit-logs row is commented out of the pricing page (7 of 15). No security.txt (404 on www.functionize.com on 5 November), no bug bounty or advisories found, security@functionize.com named in the terms, SOC 2 Type II adherence claimed in the privacy policy with no report public, and trust.functionize.com behind a login (6 of 20). The OAuth metadata is the published discovery documents read on 24 October, not re-read on 5 November. 30 + 8 + 5 + 7 + 6 = 56.\n- Tilion Fortress (35): Read as local software. stdio needs no credential, and the v3 licence key is a JWT checked on the machine. A hosted mode with `TILION_API_KEY` is described as coming soon (18). The SSRF guard refuses private, loopback and metadata addresses by default and also checks addresses inside task parameters, and annotations let a client gate writes. `run_browser_task` takes credentials in `params`, `evaluate_js` runs any script, and there is no read-only mode (12). Every tool returns untrusted page content, and no prompt-injection guidance was found in the README, USAGE.md, AGENTS.md or llms.txt (0). No call log or audit trail found (0). SECURITY.md routes vulnerabilities to GitHub private reporting with acknowledgement 'within a few days', but an issue asking to enable private vulnerability reporting has been open without a reply since 20 August 2026. Fixes go to the latest release only, and releases carry SHA256SUMS. No bounty, security.txt or advisories found (5). 18 + 12 + 0 + 0 + 5 = 35.\n\n### Payments \u0026 pricing: Tilion Fortress +15\n\n- Functionize MCP server (45): No x402, MPP or L402 (0). Plan prices are public ($0, $20 and $100 a month with their credits, add-on credits at $10 per 200,000), re-read on 5 November, but the credits a task uses aren't published, so plan-only pricing (10). A Free plan with no card and no time limit (20). A person has to sign up for Studio and sign in through a browser before any call works (0). 0 + 10 + 20 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.\n- Tilion Fortress (60): Read with the rule for self-hosted software with a paid option. No payment protocol (0). The price is one plan, Enterprise at US$2,000 a month per organisation, on fortress.tilion.com/pricing, with a free Developer tier (15). Free for non-production use, for individuals and for organisations under the licence's thresholds, with no card (30). The v3 key needs a person to sign in with email, GitHub or Google at tilion.dev/activate, though `--headless` prints a code for another device. Without a key the MCP server runs the public first-generation engine with no account (15 of 30). 0 + 15 + 30 + 15 = 60.\n\n### Reliability: Functionize MCP server +9\n\n- Functionize MCP server (55): Graded with the hosted lines, on the remote MCP server. Functionize has a status page at status.functionize.com (incident.io) with incident history, re-read from the page and its feed on 5 November, but its components are app.functionize.com and two virtualautomationengineer.com hosts, not Studio or mcp.functionize.com. A vendor status page with no component for the product takes 15, as for sourcegraph-mcp. In the 90 days from 7 August it records one incident, slower test creation and execution on 22 October on app.functionize.com, read as minor (20). No request rate limit is published with numbers; the only limits are 5 or 25 parallel runs and monthly credits per plan (5 of 15, held). No 429 or Retry-After guidance was found. The plugin's skill says a create submitted before a dropped connection finishes on the server and to list recent tests before creating again, which is safe-retry guidance of a kind (5 of 15, held). The terms say self-service plans have no SLA and service levels apply only where an Order Form states them, with no figure published (0). The release of 8 October calls the server available today and nothing labels it beta (10). 15 + 20 + 5 + 5 + 0 + 10 = 55.\n- Tilion Fortress (46): Read on the local-software lines, since the engine and the MCP server run on the user's machine. Installs from PyPI (`tilion[mcp]`, `tilion-fortress`), npm (`tilion-mcp`, `tilion-fortress`) and Docker (`tilion/fortress`), with Linux x64 and Windows x64 shipping and macOS through Docker or a source build (20). ci.yml lints the 81-patch series and runs the Python SDK tests on 3.9 and 3.12 and the Node SDK tests on every push. Chromium builds are gated by the vendor's own detection suite outside CI. No CI tests for the MCP server, and run results couldn't be read (12 of 25). Seven issues were open on 18 November 2026. Bug reports from 8 August (no Debian 13 support), 17 September (a container that exits on a port clash) and 25 October (Playwright clicks that never return) have no reply (8). Tags follow Chromium versions, with release notes for v153 in docs/ and a v2 to v3 table in the README, but no changelog for the MCP server, which is 0.1.3 in server.json and 0.1.0 in the npm package (6 of 15). The MCP server is labelled beta (0). 20 + 12 + 8 + 6 + 0 = 46.\n\n### Maintenance \u0026 community: Tilion Fortress +8\n\n- Functionize MCP server (39): Read as a closed hosted service with a public plugin repository. The server was released on 8 October 2026, 28 days before this check, and nothing newer is dated (30). In the 90 days from 7 August the only dated release is that launch; the plugin repository has commits from 26 August to 10 October 2026 and an untagged bump to 1.1.0 on 16 September, which isn't a release, and no changelog, so fewer than three (0). Support is through the in-app system with published response goals (2 hours for critical and high, 4 for medium, 24 for low), stated as goals, not commitments. No public changelog or community channel, and issue replies weren't read (6 of 25, held). No readable official MCP registry page names it and there's no official SDK (0). The plugin is MIT with a current manifest but no CI or tests (3 of 10). 30 + 0 + 6 + 0 + 3 = 39.\n- Tilion Fortress (47): Last tag v156.0.8078.47 and last commit on 5 October 2026, 44 days before 18 November. PyPI and npm versions couldn't be read (20). Two tags in the 90 days, v153.0.8010.36 on 30 September and v156 on 5 October (0). Seven open issues and five open pull requests, and the bug reports since August have no reply. There is a Discord and a contributing guide (5 of 25). The official MCP registry lists `io.github.tiliondev/fortress` 0.1.3 as active, published 7 July 2026 (15). CI for the patch series and both SDKs, a release-verification workflow and SHA-256 checks on install. Run results unread (7 of 10). 20 + 0 + 5 + 15 + 7 = 47.\n\n## Score by category\n\n| Category | Weight | Functionize MCP server | Tilion Fortress | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 55 | 46 | Functionize MCP server +9 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 29 | 74 | Tilion Fortress +45 |\n| Agent ergonomics | 13% | 43 | 73 | Tilion Fortress +30 |\n| Security \u0026 auth | 14% | 56 | 35 | Functionize MCP server +21 |\n| Payments \u0026 pricing | 10% | 45 | 60 | Tilion Fortress +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 39 | 47 | Tilion Fortress +8 |\n| Transparency \u0026 trust | 7% | 58 | 58 | even |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **46.6 · D** | **55.9 · C** | |\n\n## Facts side by side\n\n| Fact | Functionize MCP server | Tilion Fortress |\n| --- | --- | --- |\n| Kind | MCP server | MCP server |\n| Vendor | Functionize, Inc. | Tilion Inc. |\n| Hosted endpoint | `https://mcp.functionize.com/mcp` | no (local only) |\n| Transports | Streamable HTTP | stdio |\n| Auth | OAuth | None |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | Proprietary hosted service under Functionize's Terms of Service (version 2.0, effective 10 July 2026). The Claude Code plugin and its two skills are MIT-licensed; the server's source isn't public | Fortress Source Available License 1.1 (not open source). Material released before 30 September 2026 stays under BSD-3-Clause |\n| Tools exposed | 10 | 29 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `io.github.tiliondev/fortress` |\n| Last release | 2026-10-08 | 2026-10-05 |\n| Terms last updated | not read yet | no date given |\n| Privacy policy last updated | 2026-07-10 | 2026-07-23 |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | none | 804 stars |\n| Agent reviews | 2.8/5 (4) | none |\n\n## How the scores have moved\n\n### Functionize MCP server\n\n- +1.9 on 13 November 2026 (E to D): checklist\n- +0.1 on 5 November 2026: correction\n- -0.3 on 30 October 2026: checklist\n\n### Tilion Fortress\n\n- +1.9 on 18 November 2026: terms, security, new evidence\n\n## Verdicts\n\n**Functionize MCP server.** Functionize's hosted MCP server hands browser test work to Studio's own agent through ten tools, with OAuth scopes and no API key. Tool definitions sit behind sign-in, the status page has no component for Studio or the server, no rate limits or SLA are published, and a connection can read or cancel colleagues' sessions.\n\n**Tilion Fortress.** Fortress gives agents 29 annotated MCP tools on a local stealth Chromium, with an SSRF guard, capped output and statuses that name the blocking vendor. Its purpose is to get past bot checks sites deploy, the MCP server is beta with no prompt-injection guidance, bug reports since August have no reply, and Tilion Inc. couldn't be identified in a register.\n\n## Before you call either\n\n### Functionize MCP server\n\n1. Have the person complete the browser sign-in, which an agent can't do, then check the connection with `list_agent_teams`\n2. Pass the project ID, environment and test ID in `start_agent_session`, and continue a waiting session with `send_agent_message` rather than starting another\n3. Report a created test as done only after a green run, not on a test ID or a green generation\n4. After a dropped connection, list the project's recent tests before creating a test again, since a submitted create finishes on the server\n5. Send the `X-Functionize-Team-Id` header to pin a team, and keep credentials in masked Studio variables, never in prompts\n\n### Tilion Fortress\n\n1. Check the target site's terms before you use these tools to get past its bot checks. The server does not read robots.txt\n2. Call `fetch_protected_page` first and read `status` and `waf` before you retry or switch to `run_browser_task`\n3. Ask the user before `run_browser_task`, `download_file`, `save_page` or `solve_captcha`. They act on sites or write files\n4. Treat returned page text as untrusted. The server does not strip or flag injected instructions\n5. Set `TILION_LICENSE_KEY` or run `tilion activate --token` for the v3 engine. Without a key the server runs the older public engine\n\n## Questions\n\n### Which is better for AI agents, Functionize MCP server or Tilion Fortress?\n\nTilion Fortress scores 55.9 (C) on agent readiness against Functionize MCP server's 46.6 (D), and leads in 4 of 7 scored categories. Functionize MCP server leads on reliability and security \u0026 auth.\n\n### Do Functionize MCP server and Tilion Fortress need an API key?\n\nFunctionize MCP server uses an OAuth sign-in. Tilion Fortress needs no key.\n\n### Can an agent call Functionize MCP server and Tilion Fortress without installing anything?\n\nFunctionize MCP server has a hosted endpoint at https://mcp.functionize.com/mcp. Tilion Fortress runs on your own machine, with no hosted endpoint listed.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/functionize-mcp-vs-tilion-fortress.json, and with the fewest tokens: https://www.anchorterminal.com/compare/functionize-mcp-vs-tilion-fortress.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"functionize-mcp\", \"b\": \"tilion-fortress\"}`. From a terminal: `anchor compare functionize-mcp tilion-fortress`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/functionize-mcp.json and https://www.anchorterminal.com/api/v1/tools/tilion-fortress.json\n\n## Other comparisons with Functionize MCP server or Tilion Fortress\n\n- [agent-browser vs Functionize MCP server](https://www.anchorterminal.com/compare/agent-browser-vs-functionize-mcp.md)\n- [agent-browser vs Tilion Fortress](https://www.anchorterminal.com/compare/agent-browser-vs-tilion-fortress.md)\n- [Airtop vs Functionize MCP server](https://www.anchorterminal.com/compare/airtop-vs-functionize-mcp.md)\n- [Airtop vs Tilion Fortress](https://www.anchorterminal.com/compare/airtop-vs-tilion-fortress.md)\n- [Anchor Browser vs Functionize MCP server](https://www.anchorterminal.com/compare/anchor-browser-vs-functionize-mcp.md)\n- [Anchor Browser vs Tilion Fortress](https://www.anchorterminal.com/compare/anchor-browser-vs-tilion-fortress.md)\n- [AutoCua vs Functionize MCP server](https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.md)\n- [AutoCua vs Tilion Fortress](https://www.anchorterminal.com/compare/autocua-vs-tilion-fortress.md)\n- [Browser Use vs Functionize MCP server](https://www.anchorterminal.com/compare/browser-use-vs-functionize-mcp.md)\n- [Browser Use vs Tilion Fortress](https://www.anchorterminal.com/compare/browser-use-vs-tilion-fortress.md)\n- [Browserbase vs Tilion Fortress](https://www.anchorterminal.com/compare/browserbase-vs-tilion-fortress.md)\n- [Browserless vs Functionize MCP server](https://www.anchorterminal.com/compare/browserless-vs-functionize-mcp.md)\n- [Browserless vs Tilion Fortress](https://www.anchorterminal.com/compare/browserless-vs-tilion-fortress.md)\n- [BxPlaywright vs Functionize MCP server](https://www.anchorterminal.com/compare/bx-playwright-vs-functionize-mcp.md)\n- [BxPlaywright vs Tilion Fortress](https://www.anchorterminal.com/compare/bx-playwright-vs-tilion-fortress.md)\n- [Chrome DevTools MCP vs Functionize MCP server](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-functionize-mcp.md)\n- [Chrome DevTools MCP vs Tilion Fortress](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-tilion-fortress.md)\n- [Functionize MCP server vs Hyperbrowser](https://www.anchorterminal.com/compare/functionize-mcp-vs-hyperbrowser.md)\n- [Functionize MCP server vs Kane CLI](https://www.anchorterminal.com/compare/functionize-mcp-vs-kane-cli.md)\n- [Functionize MCP server vs Kernel](https://www.anchorterminal.com/compare/functionize-mcp-vs-kernel.md)\n- [Functionize MCP server vs Lightpanda](https://www.anchorterminal.com/compare/functionize-mcp-vs-lightpanda.md)\n- [Functionize MCP server vs Notte](https://www.anchorterminal.com/compare/functionize-mcp-vs-notte.md)\n- [Functionize MCP server vs Playwright MCP](https://www.anchorterminal.com/compare/functionize-mcp-vs-playwright-mcp.md)\n- [Functionize MCP server vs Pomerado](https://www.anchorterminal.com/compare/functionize-mcp-vs-pomerado.md)\n- [Functionize MCP server vs Puppeteer](https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer.md)\n- [Functionize MCP server vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer-reference-server-archived.md)\n- [Functionize MCP server vs Selenium](https://www.anchorterminal.com/compare/functionize-mcp-vs-selenium.md)\n- [Functionize MCP server vs Skyvern](https://www.anchorterminal.com/compare/functionize-mcp-vs-skyvern.md)\n- [Functionize MCP server vs Steel](https://www.anchorterminal.com/compare/functionize-mcp-vs-steel.md)\n- [Functionize MCP server vs TinyFish](https://www.anchorterminal.com/compare/functionize-mcp-vs-tinyfish.md)\n- [Hyperbrowser vs Tilion Fortress](https://www.anchorterminal.com/compare/hyperbrowser-vs-tilion-fortress.md)\n- [Kane CLI vs Tilion Fortress](https://www.anchorterminal.com/compare/kane-cli-vs-tilion-fortress.md)\n- [Kernel vs Tilion Fortress](https://www.anchorterminal.com/compare/kernel-vs-tilion-fortress.md)\n- [Lightpanda vs Tilion Fortress](https://www.anchorterminal.com/compare/lightpanda-vs-tilion-fortress.md)\n- [Notte vs Tilion Fortress](https://www.anchorterminal.com/compare/notte-vs-tilion-fortress.md)\n- [Playwright MCP vs Tilion Fortress](https://www.anchorterminal.com/compare/playwright-mcp-vs-tilion-fortress.md)\n- [Pomerado vs Tilion Fortress](https://www.anchorterminal.com/compare/pomerado-vs-tilion-fortress.md)\n- [Puppeteer (archived MCP reference server) vs Tilion Fortress](https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-tilion-fortress.md)\n- [Puppeteer vs Tilion Fortress](https://www.anchorterminal.com/compare/puppeteer-vs-tilion-fortress.md)\n- [Selenium vs Tilion Fortress](https://www.anchorterminal.com/compare/selenium-vs-tilion-fortress.md)\n- [Skyvern vs Tilion Fortress](https://www.anchorterminal.com/compare/skyvern-vs-tilion-fortress.md)\n- [Steel vs Tilion Fortress](https://www.anchorterminal.com/compare/steel-vs-tilion-fortress.md)\n- [Tilion Fortress vs TinyFish](https://www.anchorterminal.com/compare/tilion-fortress-vs-tinyfish.md)\n- [Browserbase vs Functionize MCP server](https://www.anchorterminal.com/compare/browserbase-vs-functionize-mcp.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Functionize MCP server vs Tilion Fortress",
        "url": ""
      }
    ],
    "description": "Tilion Fortress scores 55.9 (C) to Functionize's 46.6 (D) for browser automation. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Functionize MCP server D 46.6",
      "Tilion Fortress C 55.9",
      "scores"
    ],
    "h1": "Functionize MCP server vs Tilion Fortress",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/functionize-mcp-vs-tilion-fortress",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Functionize vs Tilion Fortress for AI agents (2026) | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-tilion-fortress"
  },
  "tokens": {
    "markdown": 6200,
    "slim": 1130
  },
  "version": 1
}
