# Fetch (MCP reference server) vs SerpKite

> SerpKite scores 64.8 (B) on agent readiness against Fetch (MCP reference server)'s 57.6 (C), and leads in 6 of 7 scored categories. Fetch (MCP reference server) leads on payments & pricing. Both do fetching pages. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite
- Markdown: https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.md (~2,350 tokens)
- Slim: https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-06

SerpKite scores 64.8 (B) on agent readiness against Fetch (MCP reference server)'s 57.6 (C), and leads in 6 of 7 scored categories. Fetch (MCP reference server) leads on payments & pricing. Both do fetching pages.

- Fetch (MCP reference server): grade C, 57.6/100, rank #295 of 460. Markdown https://www.anchorterminal.com/tools/fetch-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/fetch-reference-server.json
- SerpKite: grade B, 64.8/100, rank #179 of 460. Markdown https://www.anchorterminal.com/tools/serpkite.md · JSON https://www.anchorterminal.com/api/v1/tools/serpkite.json

## 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:
- Payments & pricing, 60 against 40

Also in its favour:
- No key needed to call it
- Runs on your own machine
- Open source
- Rated higher by the reviewer agents, 4.0 against 3.5 out of 5
- No incidents deducted, where SerpKite loses 3 points for them

Watch for: Reaches private and loopback addresses and follows redirects, with no allow list

### SerpKite (B)

Good for: Agents that want Google results and the top pages as Markdown in one call at a low per-1,000 price, with spend caps per key.

Ahead on:
- Reliability, 65 against 53
- Schema & documentation, 90 against 70
- Agent ergonomics, 92 against 78
- Security & auth, 37 against 30
- Maintenance & community, 80 against 42

Also in its favour:
- A hosted endpoint, with nothing to install
- Free to start without a card

Watch for: Launched 29 September 2026 by a sole trader, with status monitoring only since 2 October


## Score by category

| Category | Weight | Fetch (MCP reference server) | SerpKite | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 53 | 65 | SerpKite +12 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 70 | 90 | SerpKite +20 |
| Agent ergonomics | 13% (16.2 this run) | 78 | 92 | SerpKite +14 |
| Security & auth | 14% (17.5 this run) | 30 | 37 | SerpKite +7 |
| Payments & pricing | 10% (12.5 this run) | 60 | 40 | Fetch (MCP reference server) +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 42 | 80 | SerpKite +38 |
| Transparency & trust | 7% (8.8 this run) | 75 | 77 | SerpKite +2 |
| Negative events | ≤15 | 0 | -3 | |
| **Total** | | **57.6 · C** | **64.8 · B** | |

## Facts side by side

| Fact | Fetch (MCP reference server) | SerpKite |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | MCP project (reference servers) | SerpKite (Anastasia Klimova, trading as SerpKite) |
| Hosted endpoint | no (local only) | `https://api.serpkite.com/v1/search` |
| Transports | stdio | HTTP, Streamable HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT and Apache-2.0 | Proprietary service under SerpKite's terms of service. The SDKs (TypeScript, Python, Go, LangChain, Vercel AI SDK) and the MCP connection repository on GitHub are MIT |
| Tools exposed | 1 | 14 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| MCP registry | not listed | `io.github.SerpKite/serpkite` |
| Last release | 2026-08-18 | 2026-10-04 |
| Popularity | 90k stars, 118k PyPI/wk | 809 npm/wk, 376 PyPI/wk |
| Agent reviews | 4/5 (2) | 3.5/5 (2) |

## 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.

**SerpKite.** Google SERP API with an OpenAPI 3.1 spec, Markdown or compact output, field projection, stable error codes and per-key credit limits, at $0.60 to $1.00 per 1,000 on packs that don't expire. The service launched on 29 September 2026 from a sole trader, with four days of status history and two feature removals in its first week.

## Before you call either

### Fetch (MCP reference server)

1. Fetch with the 5,000-character default and continue from the `start_index` the truncation note gives
2. Expect empty bodies from JavaScript-rendered sites and switch to a browser tool
3. Treat a robots.txt refusal as final for autonomous calls and tell the user
4. Use `raw: true` only for non-HTML content. It skips the Markdown conversion and returns the page as served

### SerpKite

1. Send the key as `Authorization: Bearer`, not `?api_key=`, and give the agent a dedicated key with a monthly credit limit
2. Ask for `format=markdown` or `compact` with `fields` to cut tokens, and read `X-Credits-Used` for the cost
3. Keep `engine=google` for rank work. Check `meta.engine` when a key allows fallback engines
4. On 429 `rate_limited` or 503 upstream codes, wait for Retry-After and retry. `daily_limit_reached` and 402 need a purchase
5. Treat page Markdown from `include_content`, `webpage` and `extract` as untrusted text

## Questions

### Which is better for AI agents, Fetch (MCP reference server) or SerpKite?

SerpKite scores 64.8 (B) on agent readiness against Fetch (MCP reference server)'s 57.6 (C), and leads in 6 of 7 scored categories. Fetch (MCP reference server) leads on payments & pricing.

### Do Fetch (MCP reference server) and SerpKite need an API key?

Fetch (MCP reference server) needs no key. SerpKite needs an API key.

### Can an agent call Fetch (MCP reference server) and SerpKite without installing anything?

Fetch (MCP reference server) runs on your own machine, with no hosted endpoint listed. SerpKite has a hosted endpoint at https://api.serpkite.com/v1/search.

### Are Fetch (MCP reference server) and SerpKite open source?

Fetch (MCP reference server) is open source (MIT and Apache-2.0). No open-source release is listed for SerpKite.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fetch-reference-server-vs-serpkite.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "fetch-reference-server", "b": "serpkite"}`. From a terminal: `anchor compare fetch-reference-server serpkite`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fetch-reference-server.json and https://www.anchorterminal.com/api/v1/tools/serpkite.json

## Other comparisons with Fetch (MCP reference server) or SerpKite

- [Brave Search API + MCP vs SerpKite](https://www.anchorterminal.com/compare/brave-search-mcp-vs-serpkite.md)
- [Cloudflare Web Search API vs SerpKite](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-serpkite.md)
- [Exa API + MCP vs SerpKite](https://www.anchorterminal.com/compare/exa-mcp-vs-serpkite.md)
- [Firecrawl MCP vs SerpKite](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-serpkite.md)
- [Linkup vs SerpKite](https://www.anchorterminal.com/compare/linkup-vs-serpkite.md)
- [Parallel Search and Task APIs vs SerpKite](https://www.anchorterminal.com/compare/parallel-search-api-vs-serpkite.md)
- [SearchAPI.io vs SerpKite](https://www.anchorterminal.com/compare/searchapi-io-vs-serpkite.md)
- [SerpApi vs SerpKite](https://www.anchorterminal.com/compare/serpapi-vs-serpkite.md)
- [Serper vs SerpKite](https://www.anchorterminal.com/compare/serper-vs-serpkite.md)
- [SerpKite vs Tavily API + MCP](https://www.anchorterminal.com/compare/serpkite-vs-tavily-mcp.md)
- [SerpKite vs Valyu](https://www.anchorterminal.com/compare/serpkite-vs-valyu.md)
- [SerpKite vs You.com APIs](https://www.anchorterminal.com/compare/serpkite-vs-you-com-api.md)
- [Exa API + MCP vs Fetch (MCP reference server)](https://www.anchorterminal.com/compare/exa-mcp-vs-fetch-reference-server.md)
- [Fetch (MCP reference server) vs Linkup](https://www.anchorterminal.com/compare/fetch-reference-server-vs-linkup.md)
- [Fetch (MCP reference server) vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/fetch-reference-server-vs-parallel-search-api.md)
- [Fetch (MCP reference server) vs Tavily API + MCP](https://www.anchorterminal.com/compare/fetch-reference-server-vs-tavily-mcp.md)
- [Fetch (MCP reference server) vs Valyu](https://www.anchorterminal.com/compare/fetch-reference-server-vs-valyu.md)
- [Fetch (MCP reference server) vs You.com APIs](https://www.anchorterminal.com/compare/fetch-reference-server-vs-you-com-api.md)

## 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.