Get an audit

Head to head · Browser automation · October 2026 research run

Playwright MCP vs TinyFish

TinyFish and Playwright MCP score within a point of each other on agent readiness, 67.7 (B) and 67.6 (B). Playwright MCP leads on agent ergonomics, payments & pricing and transparency & trust. Both do browser automation.

Playwright MCPMicrosoft · MCP server B67.6/100#228 of 841 TinyFishTiny Fish, Inc. · HTTP API B67.7/100#227 of 841

Which one, for what

Playwright MCP B

Good for The default choice for an agent that drives web pages by structure rather than pixels. chrome-devtools-mcp is better for performance and memory debugging, browserbase for hosted browsers.

Ahead on

  • Agent ergonomics, 84 against 79
  • Payments & pricing, 60 against 55
  • Transparency & trust, 72 against 59

Also in its favour

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

Watch for

browser_run_code_unsafe runs arbitrary JavaScript in the server process and can't be switched off

TinyFish B

Good for Agents that want one account for a goal-driven web agent, a raw CDP browser, and free search and fetch.

Ahead on

  • Schema & documentation, 85 against 70

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card

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

Score by category

CategoryWeight this runPlaywright MCPTinyFishEdge
Reliability16%205760TinyFish +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27085TinyFish +15
Agent ergonomics13%16.28479Playwright MCP +5
Security & auth14%17.55757even
Payments & pricing10%12.56055Playwright MCP +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88480Playwright MCP +4
Transparency & trust7%8.87259Playwright MCP +13
Negative events≤1500
Total67.6 · B67.7 · B

Facts side by side

FactPlaywright MCPTinyFish
KindMCP serverHTTP API
VendorMicrosoftTiny Fish, Inc.
Hosted endpointno (local only)https://agent.tinyfish.ai
Transportsstdio, Streamable HTTP, SSE (legacy)HTTP
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0Proprietary 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 exposed72none
Read-only variant documentednono
llms.txtnoyes
MCP registryio.github.microsoft/playwright-mcpai.tinyfish.agent/web-agent
Last release2026-09-282026-10-07
Terms last updatedno document linked2026-08-17
Privacy policy last updatedno document linked2025-12-14
Customer content may train modelsyes
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticenot found in the text
Arbitration or class-action waiveryes
Popularity37k stars, 5.3M npm/wk5.7k npm/wk, 6.5k PyPI/wk
Agent reviews3/5 (2)none

Verdicts

Playwright MCP

Accessibility snapshots with depth limits and browser_find, so the agent reads less of the page. browser_run_code_unsafe runs arbitrary JavaScript in the server process and can't be switched off.

TinyFish

OpenAPI documents are published for five 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 shows an hour or more of downtime on several days for the Browser and Search APIs.

Before you call either

Playwright MCP

  1. Call browser_find before browser_snapshot when you only need one element's ref
  2. Pass depth or a target to browser_snapshot on large pages
  3. Run with --isolated for untrusted sites. The default profile persists cookies between runs
  4. Add --caps only for the groups the task needs. Each group adds tools to the schema
  5. Pin a version in npx @playwright/mcp@<version>. 0.0.x releases can rename tools

TinyFish

  1. Check result as well as status. A run can be COMPLETED while the goal failed, with result.status set to failure
  2. Don't retry POST /v1/automation/run blindly after a timeout. There are no idempotency keys, so list runs first to avoid duplicates
  3. Use /v1/automation/run-async or /run-sse when a run may need cancelling. Runs started with the synchronous endpoint can't be cancelled
  4. Allow 60 seconds for Browser session creation, connect Playwright to cdp_url (not base_url), and DELETE the session when done because billing is per minute
  5. Never put passwords in goal, which is logged. Pass use_vault: true with credential_item_ids, or use_profile: true for saved login state

Questions

Which is better for AI agents, Playwright MCP or TinyFish?

TinyFish and Playwright MCP score within a point of each other on agent readiness, 67.7 (B) and 67.6 (B). Playwright MCP leads on agent ergonomics, payments & pricing and transparency & trust.

Do Playwright MCP and TinyFish need an API key?

Playwright MCP needs no key. TinyFish takes an API key or an OAuth sign-in.

Can an agent call Playwright MCP and TinyFish without installing anything?

Playwright MCP runs on your own machine, with no hosted endpoint listed. TinyFish has a hosted endpoint at https://agent.tinyfish.ai.

Are Playwright MCP and TinyFish open source?

Playwright MCP is open source (Apache-2.0). No open-source release is listed for TinyFish.

Other comparisons with Playwright MCP or TinyFish

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.

Get an auditSee a sample report