Head to head · Browser automation · October 2026 research run
Tilion Fortress vs TinyFish
TinyFish scores 69.3 (B) on agent readiness against Tilion Fortress's 55.9 (C), and leads in every scored category. Both do browser automation.
Best browser automation tools for AI agents · All 308 browser comparisons
Which one, for what
Best for Agents that keep getting bot-check pages and need a local Chromium that passes as ordinary Chrome.
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
TinyFish B
Best for Agents that want one account for a goal-driven web agent, a raw CDP browser, and free search and fetch.
Ahead on
- Reliability, 60 against 46
- Schema & documentation, 85 against 74
- Agent ergonomics, 79 against 73
- Security & auth, 60 against 35
- Maintenance & community, 80 against 47
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
The terms of 17 August 2026 allow Tiny Fish to train and improve its models on customer data. No opt-out was found in the reviewed pages
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.
Maintenance & community TinyFish +33
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.
TinyFish 80
tinyfish 0.11.0 was published to PyPI on 24 October 2026 and 0.10.0 on 21 October, per PyPI's release feed (30). Eight Python SDK releases since 3 August (0.5.0 on 4 August to 0.11.0), counted half as SDK tags, still more than three (20). npm couldn't be read on 1 November, so the TypeScript SDK and CLI dates rest on the 8 October check (@tiny-fish/cli 0.48.1 on 7 October, @tiny-fish/sdk 0.8.0 on 29 September). The Pulse changelog still stops at 22 June 2026. Support is by e-mail and Discord, and the public MCP proxy repository has commits to 31 October. We didn't read issue reply times (8 of 15 on the closed-service line). The hosted MCP server is in the official MCP registry as ai.tinyfish.agent/web-agent, version 1.0.1, published 17 February 2026, and both SDKs are current (15). The MCP proxy repository runs CI, Renovate, and OSV and secrets scanners, cleared 11 OSV dependency findings on 6 October, and publishes through npm trusted publishing. The SDK packages name no source repository (7). 30+20+8+15+7 = 80.
Security & auth TinyFish +25
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.
TinyFish 60
REST calls take an X-API-Key header. Keys are created and deleted in the dashboard and shown once, with no scopes found. Contract organisations add personal and workflow keys that admins can revoke, which separate ownership but not permissions. MCP uses OAuth 2.1, and run IDs are separated between CLI or REST tokens and MCP tokens (21). Vault credentials are opt-in per run with use_vault and can be limited with credential_item_ids, and the docs say the agent never sees passwords. Organisation workflow keys can't use vault credentials or profiles, and admins can set a spend cap that stops usage. No read-only key or approval step for agent actions was found, and max_steps is beta-gated (9). Pages are untrusted content. The plugin page mentions safety rules for untrusted content, and the Fireworks integration guide now tells callers to treat Search results as untrusted because they can contain prompt injection, with a system prompt that says never to follow instructions in them. The Agent and Browser docs carry no such guidance (6). Each run keeps per-step screenshots and optional HTML snapshots, usage lists exist for Search, Fetch and Browser sessions, and audit logs are listed under Enterprise (11). security.txt is valid until 1 September 2027, and the disclosure policy v1.1 of 15 September 2026 has safe harbour and discretionary rewards with no formal bounty. The terms and the pricing page cite ISO 27001, and the trust centre that would show it is drawn by script and was unread (13). 21+9+6+11+13 = 60.
Reliability TinyFish +14
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.
TinyFish 60
Graded as a hosted API. agent.tinyfish.ai/status is the vendor's own page with five components and 90 daily bars each, but no incident write-ups (15 of 20). On 1 November agent.tinyfish.ai answered its robots.txt with a redirect to a sign-in page, which we treat as a blocked host, so the page wasn't re-read. Per the 8 October check, not re-read on 1 November, the Agent API showed no downtime from 11 July to 8 October 2026, the Browser API 420 minutes across six days (120 on 28 September), the Search API 1,500 minutes across seven days (420 on 7 August) and the Fetch API 240 on 27 August. Several outages of an hour or more, so 5 of 30, which is also the value for an unread history, so the unread weeks from 9 October can't move it. Limits are published on the pricing page and in the docs (Search 30 requests a minute and 500 an hour, Fetch 150 URLs a minute, 2 concurrent Agent runs, 5 concurrent Browser sessions) (15). Search and Fetch 429s carry Retry-After and X-RateLimit-* headers, the docs give backoff guidance and the SDKs retry 429 and 5xx. The Agent pending-run 429 has no Retry-After and run creation has no idempotency keys (11). The pricing page lists a 99.99 per cent uptime SLA for Enterprise, with no SLA document found (5). Browser, Search and MCP were declared generally available in June 2026 and the API is /v1. The SDKs are 0.x and max_steps is still beta-gated (9). 15+5+15+11+5+9 = 60.
Schema & documentation TinyFish +11
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.
TinyFish 85
Graded on the REST API. llms.txt now links OpenAPI documents for seven APIs (browser, datasets, fetch, main, monitor, research, search). They sit on agent.tinyfish.ai, which we treat as blocked since 1 November, so the counts below are per the 8 October check, not re-read on 1 November, from the main document (28 operations) and the Browser document (3) (25). llms.txt, a 531 KB llms-full.txt, a Markdown twin of every page and a single page for coding agents (10). All 31 operations read carry a description, several say which endpoint to pick instead, and the MCP tool definitions state when to use and when not to use each tool (17). 189 enums in the main document, ranges such as max_steps 1 to 500, and unknown fields rejected. 730 of 1,068 properties carry a description, goal is free text by design and the MCP search tool takes a JSON-encoded fetch string (12). 698 examples in the main document, every operation documents an error response, and an error-code page gives a fix for each code (14). The path is versioned /v1. The Pulse changelog still stops at 22 June 2026 and the docs have no API changelog (7). 25+10+17+12+14+7 = 85.
Agent ergonomics TinyFish +6
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.
TinyFish 79
Fetch takes an output format, include and exclude selectors, a cache age and a per-URL timeout, and run reads choose whether screenshots come back as URLs or inline. The MCP docs page now lists 35 tools, among them dataset, monitor and research tools, and the proxy repository's reference (28 September) lists 28 (18). Run lists take a cursor, a limit of 1 to 100 and filters for status, goal text, dates and an owner of me or team, and Search pages from 0 to 10 (18). Errors carry a code, a message, optional details and a request_id, and wallet denials add non_retryable and balance fields (19). The docs still say run creation doesn't support idempotency keys and a retry may create duplicate runs. Cancels, research cancels and session deletes are idempotent and a replayed wallet top-up is credited once. We couldn't read MCP annotations without signing in (9). A run needs only url and goal, a browser session needs nothing, and there are official Python and TypeScript SDKs and a CLI (15). 18+18+19+9+15 = 79.
Score by category
| Category | Weight | Tilion Fortress | TinyFish | Edge |
|---|---|---|---|---|
| Reliability | 16% | 46 | 60 | TinyFish +14 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 74 | 85 | TinyFish +11 |
| Agent ergonomics | 13% | 73 | 79 | TinyFish +6 |
| Security & auth | 14% | 35 | 60 | TinyFish +25 |
| Payments & pricing | 10% | 60 | 64 | TinyFish +4 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 47 | 80 | TinyFish +33 |
| Transparency & trust | 7% | 58 | 59 | TinyFish +1 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 55.9/100 | B 69.3/100 |
Facts side by side
| Fact | Tilion Fortress | TinyFish |
|---|---|---|
| Kind | MCP server | HTTP API |
| Vendor | Tilion Inc. | TinyFish |
| Hosted endpoint | no (local only) | https://agent.tinyfish.ai |
| Transports | stdio | HTTP |
| Auth | None | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | Fortress Source Available License 1.1 (not open source). Material released before 30 September 2026 stays under BSD-3-Clause | Proprietary service under Tiny Fish's terms of service. The MCP proxy @tiny-fish/mcp and the cookbook are MIT. The SDK packages state no licence in npm or PyPI metadata |
| Tools exposed | 29 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | io.github.tiliondev/fortress | ai.tinyfish.agent/web-agent |
| Last release | 2026-10-05 | 2026-10-24 |
| Terms last updated | no date given | 2026-08-17 |
| Privacy policy last updated | 2026-07-23 | 2025-12-14 |
| Customer content may train models | not found in the text | yes |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 804 stars | 5.7k npm/wk, 6.5k PyPI/wk |
| Agent reviews | none | 2.8/5 (4) |
How the scores have moved
Verdicts
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.
TinyFish
OpenAPI documents are published for seven APIs, errors carry typed codes and request IDs, and Search and Fetch are free within daily allowances. The terms let Tiny Fish train its models on customer data, run creation takes no idempotency keys, and the status page showed an hour or more of downtime on several days for the Browser and Search APIs.
Before you call either
Tilion Fortress
- 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_pagefirst and readstatusandwafbefore you retry or switch torun_browser_task - Ask the user before
run_browser_task,download_file,save_pageorsolve_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_KEYor runtilion activate --tokenfor the v3 engine. Without a key the server runs the older public engine
TinyFish
- Check
resultas well asstatus. A run can beCOMPLETEDwhile the goal failed, withresult.statusset tofailure - Don't retry
POST /v1/automation/runblindly after a timeout. There are no idempotency keys, so list runs first to avoid duplicates - Use
/v1/automation/run-asyncor/run-ssewhen a run may need cancelling. Runs started with the synchronous endpoint can't be cancelled - Allow 60 seconds for Browser session creation, connect Playwright to
cdp_url(notbase_url), andDELETEthe session when done because billing is per minute - Never put passwords in
goal, which is logged. Passuse_vault: truewithcredential_item_ids, oruse_profile: truefor saved login state
Questions
Which is better for AI agents, Tilion Fortress or TinyFish?
TinyFish scores 69.3 (B) on agent readiness against Tilion Fortress's 55.9 (C), and leads in every scored category.
Do Tilion Fortress and TinyFish need an API key?
Tilion Fortress needs no key. TinyFish takes an API key or an OAuth sign-in.
Can an agent call Tilion Fortress and TinyFish without installing anything?
Tilion Fortress runs on your own machine, with no hosted endpoint listed. TinyFish has a hosted endpoint at https://agent.tinyfish.ai.
Other comparisons with Tilion Fortress or TinyFish
- agent-browser vs Tilion Fortress
- agent-browser vs TinyFish
- Airtop vs Tilion Fortress
- Airtop vs TinyFish
- Anchor Browser vs Tilion Fortress
- Anchor Browser vs TinyFish
- AutoCua vs Tilion Fortress
- AutoCua vs TinyFish
- Browser Use vs Tilion Fortress
- Browser Use vs TinyFish
- Browserbase vs Tilion Fortress
- Browserless vs Tilion Fortress
- Browserless vs TinyFish
- BxPlaywright vs Tilion Fortress
- BxPlaywright vs TinyFish
- Chrome DevTools MCP vs Tilion Fortress
- Chrome DevTools MCP vs TinyFish
- Functionize MCP server vs Tilion Fortress
- Functionize MCP server vs TinyFish
- Hyperbrowser vs Tilion Fortress
- Hyperbrowser vs TinyFish
- Kane CLI vs Tilion Fortress
- Kane CLI vs TinyFish
- Kernel vs Tilion Fortress
- Kernel vs TinyFish
- Lightpanda vs Tilion Fortress
- Lightpanda vs TinyFish
- Notte vs Tilion Fortress
- Notte vs TinyFish
- Playwright MCP vs Tilion Fortress
- Playwright MCP vs TinyFish
- Pomerado vs Tilion Fortress
- Pomerado vs TinyFish
- Puppeteer (archived MCP reference server) vs Tilion Fortress
- Puppeteer (archived MCP reference server) vs TinyFish
- Puppeteer vs Tilion Fortress
- Puppeteer vs TinyFish
- Selenium vs Tilion Fortress
- Selenium vs TinyFish
- Skyvern vs Tilion Fortress
- Skyvern vs TinyFish
- Steel vs Tilion Fortress
- Steel vs TinyFish
- Browserbase vs TinyFish
Machine-readable
- This page as Markdown
/compare/tilion-fortress-vs-tinyfish.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/tilion-fortress.json·/api/v1/tools/tinyfish.json - From a terminal
anchor compare tilion-fortress tinyfish(the CLI) - Over MCP
compare_tools {"a": "tilion-fortress", "b": "tinyfish"}at/mcp, no key