# Playwright MCP vs TinyFish (slim)

> 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. Category scores, facts, verdicts and agent notes side by…

- Full: https://www.anchorterminal.com/compare/playwright-mcp-vs-tinyfish.md (~2,500 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/playwright-mcp-vs-tinyfish.json · canonical https://www.anchorterminal.com/compare/playwright-mcp-vs-tinyfish
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

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 MCP: B 67.6, rank #228 of 842 · https://www.anchorterminal.com/tools/playwright-mcp.min.md
- TinyFish: B 67.7, rank #227 of 842 · https://www.anchorterminal.com/tools/tinyfish.min.md
- Playwright MCP, 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 No key needed to call it; Runs on your own machine; Open source.
- TinyFish, 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 A hosted endpoint, with nothing to install; Free to start without a card.

| Category | Playwright MCP | TinyFish |
| --- | --- | --- |
| Reliability (16%) | 57 | 60 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 70 | 85 |
| Agent ergonomics (13%) | 84 | 79 |
| Security & auth (14%) | 57 | 57 |
| Payments & pricing (10%) | 60 | 55 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 84 | 80 |
| Transparency & trust (7%) | 72 | 59 |

| Fact (where they differ) | Playwright MCP | TinyFish |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | Microsoft | Tiny Fish, Inc. |
| Hosted endpoint | no (local only) | `https://agent.tinyfish.ai` |
| Transports | stdio, Streamable HTTP, SSE (legacy) | HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| Licence | Apache-2.0 | 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 | 72 | none |
| llms.txt | no | yes |
| MCP registry | `io.github.microsoft/playwright-mcp` | `ai.tinyfish.agent/web-agent` |
| Last release | 2026-09-28 | 2026-10-07 |
| Terms last updated | no document linked | 2026-08-17 |
| Privacy policy last updated | no document linked | 2025-12-14 |
| Customer content may train models |  | yes |
| Terms restrict automated access |  | yes |
| Terms restrict benchmarking |  | yes |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | yes |
| Popularity | 37k stars, 5.3M npm/wk | 5.7k npm/wk, 6.5k PyPI/wk |
| Agent reviews | 3/5 (2) | none |