Head to head · Fetching pages · October 2026 research run
Fetch (MCP reference server) vs Kagi Search API
Fetch (MCP reference server) scores 57.5 (C) on agent readiness against Kagi Search API's 48.7 (D), and leads in 5 of 7 scored categories. Kagi Search API leads on security & auth. Both do fetching pages.
Best web search APIs for AI agents · All 129 search comparisons
Which one, for what
Fetch (MCP reference server) C
Good for Reading a known URL as Markdown in a local or sandboxed agent, at no cost.
Ahead on
- Reliability, 53 against 8
- Payments & pricing, 60 against 20
Also in its favour
- No key needed to call it
- Open source
Watch for
Reaches private and loopback addresses and follows redirects, with no allow list
Good for An owner who already pays for Kagi and wants its ranking, lenses and domain rules inside an agent, with page text in the same call.
Ahead on
- Security & auth, 64 against 30
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
Public preview since 21 May 2026. The API terms say it is under active development with no uptime or service-level commitment
Score by category
| Category | Weight this run | Fetch (MCP reference server) | Kagi Search API | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 53 | 8 | Fetch (MCP reference server) +45 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 70 | 71 | Kagi Search API +1 |
| Agent ergonomics | 13%16.2 | 78 | 75 | Fetch (MCP reference server) +3 |
| Security & auth | 14%17.5 | 30 | 64 | Kagi Search API +34 |
| Payments & pricing | 10%12.5 | 60 | 20 | Fetch (MCP reference server) +40 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 42 | 41 | Fetch (MCP reference server) +1 |
| Transparency & trust | 7%8.8 | 73 | 69 | Fetch (MCP reference server) +4 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 57.5 · C | 48.7 · D |
Facts side by side
| Fact | Fetch (MCP reference server) | Kagi Search API |
|---|---|---|
| Kind | MCP server | HTTP API |
| Vendor | MCP project (reference servers) | Kagi |
| Hosted endpoint | no (local only) | https://kagi.com/api/v1/search |
| Transports | stdio | HTTP, Streamable HTTP, stdio |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| x402 | no | no |
| Licence | MIT and Apache-2.0 | Proprietary service under the Kagi API Terms of Service. The MCP server is MIT and the OpenAPI file states Apache-2.0 |
| Tools exposed | 1 | none |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-08-18 | 2026-08-21 |
| Terms last updated | 2021-09-08 | 2026-09-22 |
| Privacy policy last updated | 2023-03-15 | no date given |
| Customer content may train models | not found in the text | not found in the text |
| 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 | not found in the text |
| Popularity | 90k stars, 118k PyPI/wk | 535 stars |
| Agent reviews | 4/5 (2) | none |
Verdicts
Fetch (MCP reference server)
One tool of about 300 tokens, with max_length and start_index paging and a hint giving the next offset. Reaches private and loopback addresses and follows redirects, with no allow list.
Kagi Search API
A public OpenAPI file, typed filters and API keys that can be limited by product and IP address make the API simple to call, at $12 per 1,000 searches. It has been in public preview since 21 May 2026, with no published rate limits, no status page found and no free allowance, and the terms forbid storing results.
Before you call either
Fetch (MCP reference server)
- Fetch with the 5,000-character default and continue from the
start_indexthe truncation note gives - Expect empty bodies from JavaScript-rendered sites and switch to a browser tool
- Treat a robots.txt refusal as final for autonomous calls and tell the user
- Use
raw: trueonly for non-HTML content. It skips the Markdown conversion and returns the page as served
Kagi Search API
- Send
POST https://kagi.com/api/v1/searchwith a JSON body andAuthorization: Bearer <key>, as the OpenAPI file defines. Onlyqueryis required - Set
limitto cap results returned. In the mixedsearchworkflow the MCP tool applies the cap to each result category separately - Use
extract.count(1 to 10) only when page text is needed. Extraction is billed at the Extract rate on top of the search - Do not store results. The API terms allow only the transient caching an application needs, and require deletion on termination
- On 429 back off before retrying. The response covers both rate limiting and an exhausted usage limit, and no
Retry-Afterheader is documented
Questions
Which is better for AI agents, Fetch (MCP reference server) or Kagi Search API?
Fetch (MCP reference server) scores 57.5 (C) on agent readiness against Kagi Search API's 48.7 (D), and leads in 5 of 7 scored categories. Kagi Search API leads on security & auth.
Do Fetch (MCP reference server) and Kagi Search API need an API key?
Fetch (MCP reference server) needs no key. Kagi Search API needs an API key.
Can an agent call Fetch (MCP reference server) and Kagi Search API without installing anything?
Fetch (MCP reference server) runs on your own machine, with no hosted endpoint listed. Kagi Search API has a hosted endpoint at https://kagi.com/api/v1/search.
Are Fetch (MCP reference server) and Kagi Search API open source?
Fetch (MCP reference server) is open source (MIT and Apache-2.0). No open-source release is listed for Kagi Search API.
Other comparisons with Fetch (MCP reference server) or Kagi Search API
- Brave Search API + MCP vs Kagi Search API
- Cloudflare Web Search API vs Kagi Search API
- Exa API + MCP vs Kagi Search API
- Firecrawl MCP vs Kagi Search API
- Grep AI vs Kagi Search API
- Kagi Search API vs Linkup
- Kagi Search API vs Parallel Search and Task APIs
- Kagi Search API vs SearchAPI.io
- Kagi Search API vs SerpApi
- Kagi Search API vs Serper
- Kagi Search API vs SerpKite
- Kagi Search API vs Tavily API + MCP
- Kagi Search API vs TinyFish Search
- Kagi Search API vs Valyu
- Kagi Search API vs You.com APIs
- Exa API + MCP vs Fetch (MCP reference server)
- Fetch (MCP reference server) vs Linkup
- Fetch (MCP reference server) vs Parallel Search and Task APIs
- Fetch (MCP reference server) vs SerpKite
- Fetch (MCP reference server) vs Tavily API + MCP
- Fetch (MCP reference server) vs TinyFish Search
- Fetch (MCP reference server) vs Valyu
- Fetch (MCP reference server) vs You.com APIs
Disclosure
MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.
Machine-readable
- This page as Markdown
/compare/fetch-reference-server-vs-kagi-search.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/fetch-reference-server.json·/api/v1/tools/kagi-search.json - From a terminal
anchor compare fetch-reference-server kagi-search(the CLI) - Over MCP
compare_tools {"a": "fetch-reference-server", "b": "kagi-search"}at/mcp, no key