Head to head · Browser automation · October 2026 research run

Functionize MCP server vs Tilion Fortress

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 & auth. Both do browser automation.

Best browser automation tools for AI agents · All 308 browser comparisons

Which one, for what

Functionize MCP server D

Best 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.

Ahead on

  • Reliability, 55 against 46
  • Security & auth, 56 against 35

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

Tool definitions, input schemas and annotations aren't published; they sit behind OAuth sign-in

Tilion Fortress C

Best for Agents that keep getting bot-check pages and need a local Chromium that passes as ordinary Chrome.

Ahead on

  • Schema & documentation, 74 against 29
  • Agent ergonomics, 73 against 43
  • Payments & pricing, 60 against 45
  • Maintenance & community, 47 against 39

Also in its favour

  • No key needed to call it
  • Runs on your own machine

Watch for

Sold to defeat bot detection (Cloudflare, DataDome, PerimeterX, Akamai) and, with a third-party key, to solve CAPTCHAs, which many sites' terms forbid

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Schema & documentation Tilion Fortress +45

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.

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.

Agent ergonomics Tilion Fortress +30

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.

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.

Security & auth Functionize MCP server +21

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.

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.

Payments & pricing Tilion Fortress +15

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.

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.

Reliability Functionize MCP server +9

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.

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.

Maintenance & community Tilion Fortress +8

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.

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.

Score by category

CategoryWeightFunctionize MCP serverTilion FortressEdge
Reliability16%5546Functionize MCP server +9
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%2974Tilion Fortress +45
Agent ergonomics13%4373Tilion Fortress +30
Security & auth14%5635Functionize MCP server +21
Payments & pricing10%4560Tilion Fortress +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%3947Tilion Fortress +8
Transparency & trust7%5858even
Negative events≤1500
TotalD 46.6/100C 55.9/100

Facts side by side

FactFunctionize MCP serverTilion Fortress
KindMCP serverMCP server
VendorFunctionize, Inc.Tilion Inc.
Hosted endpointhttps://mcp.functionize.com/mcpno (local only)
TransportsStreamable HTTPstdio
AuthOAuthNone
PricingFreemiumFreemium
x402nono
LicenceProprietary 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 publicFortress Source Available License 1.1 (not open source). Material released before 30 September 2026 stays under BSD-3-Clause
Tools exposed1029
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedio.github.tiliondev/fortress
Last release2026-10-082026-10-05
Terms last updatednot read yetno date given
Privacy policy last updated2026-07-102026-07-23
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text
Popularitynone804 stars
Agent reviews2.8/5 (4)none

How the scores have moved

Verdicts

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.

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.

Before you call either

Functionize MCP server

  1. Have the person complete the browser sign-in, which an agent can't do, then check the connection with list_agent_teams
  2. 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
  3. Report a created test as done only after a green run, not on a test ID or a green generation
  4. After a dropped connection, list the project's recent tests before creating a test again, since a submitted create finishes on the server
  5. Send the X-Functionize-Team-Id header to pin a team, and keep credentials in masked Studio variables, never in prompts

Tilion Fortress

  1. Check the target site's terms before you use these tools to get past its bot checks. The server does not read robots.txt
  2. Call fetch_protected_page first and read status and waf before you retry or switch to run_browser_task
  3. Ask the user before run_browser_task, download_file, save_page or solve_captcha. They act on sites or write files
  4. Treat returned page text as untrusted. The server does not strip or flag injected instructions
  5. Set TILION_LICENSE_KEY or run tilion activate --token for the v3 engine. Without a key the server runs the older public engine

Questions

Which is better for AI agents, Functionize MCP server or Tilion Fortress?

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 & auth.

Do Functionize MCP server and Tilion Fortress need an API key?

Functionize MCP server uses an OAuth sign-in. Tilion Fortress needs no key.

Can an agent call Functionize MCP server and Tilion Fortress without installing anything?

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.

Other comparisons with Functionize MCP server or Tilion Fortress

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.