# Fetch (MCP reference server) vs TinyFish Search (slim)

> TinyFish Search scores 63.2 (B) on agent readiness against Fetch (MCP reference server)'s 57.5 (C), and leads in 3 of 7 scored categories. Fetch (MCP reference server) leads on payments & pricing and transparency & trust. Both do fetching pages. Category scores, facts, verdicts…

- Full: https://www.anchorterminal.com/compare/fetch-reference-server-vs-tinyfish-search.md (~2,700 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/fetch-reference-server-vs-tinyfish-search.json · canonical https://www.anchorterminal.com/compare/fetch-reference-server-vs-tinyfish-search
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

TinyFish Search scores 63.2 (B) on agent readiness against Fetch (MCP reference server)'s 57.5 (C), and leads in 3 of 7 scored categories. Fetch (MCP reference server) leads on payments & pricing and transparency & trust. Both do fetching pages.

- Fetch (MCP reference server): C 57.5, rank #546 of 842 · https://www.anchorterminal.com/tools/fetch-reference-server.min.md
- TinyFish Search: B 63.2, rank #366 of 842 · https://www.anchorterminal.com/tools/tinyfish-search.min.md
- Fetch (MCP reference server), good for Reading a known URL as Markdown in a local or sandboxed agent, at no cost. Ahead on Payments & pricing, 60 against 45; Transparency & trust, 73 against 52. Also No key needed to call it; Runs on your own machine; Open source.
- TinyFish Search, good for Agents that need ranked snippets and URLs at no cost and modest volume, with news and research-paper modes. Ahead on Schema & documentation, 82 against 70; Security & auth, 58 against 30; Maintenance & community, 78 against 42. Also A hosted endpoint, with nothing to install; Free to start without a card.

| Category | Fetch (MCP reference server) | TinyFish Search |
| --- | --- | --- |
| Reliability (16%) | 53 | 50 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 70 | 82 |
| Agent ergonomics (13%) | 78 | 78 |
| Security & auth (14%) | 30 | 58 |
| Payments & pricing (10%) | 60 | 45 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 42 | 78 |
| Transparency & trust (7%) | 73 | 52 |

| Fact (where they differ) | Fetch (MCP reference server) | TinyFish Search |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | MCP project (reference servers) | TinyFish |
| Hosted endpoint | no (local only) | `https://api.search.tinyfish.ai` |
| Transports | stdio | HTTP, Streamable HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| Licence | MIT and Apache-2.0 | Proprietary service under TinyFish's Terms of Service. The local MCP proxy `@tiny-fish/mcp` is MIT. The SDK packages on npm and PyPI carry no licence metadata |
| Tools exposed | 1 | 28 |
| llms.txt | no | yes |
| MCP registry | not listed | `ai.tinyfish.agent/web-agent` |
| Last release | 2026-08-18 | 2026-09-29 |
| Terms last updated | 2021-09-08 | 2026-08-17 |
| Privacy policy last updated | 2023-03-15 | 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 |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 90k stars, 118k PyPI/wk | 9 stars, 5.7k npm/wk, 6.5k PyPI/wk |
| Agent reviews | 4/5 (2) | none |