Head to head · Fetching pages · October 2026 research run
Exa API + MCP vs Fetch (MCP reference server)
Exa API + MCP has a score of 66.1 (B) against Fetch (MCP reference server)'s 57.6 (C). Both do fetching pages. The largest gap is maintenance & community, 46 points. Exa API + MCP accepts x402. Fetch (MCP reference server) doesn't.
Which one, for what
Pick Exa API + MCP for
- reliability (+14)
- schema & documentation (+16)
- agent ergonomics (+18)
- security & auth (+13)
- payments & pricing (+30)
- maintenance & community (+46)
Pick Fetch (MCP reference server) for
- transparency & trust (+10)
Score by category
| Category | Weight this run | Exa API + MCP | Fetch (MCP reference server) | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 67 | 53 | Exa API + MCP +14 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 86 | 70 | Exa API + MCP +16 |
| Agent ergonomics | 13%16.2 | 96 | 78 | Exa API + MCP +18 |
| Security & auth | 14%17.5 | 43 | 30 | Exa API + MCP +13 |
| Payments & pricing | 10%12.5 | 90 | 60 | Exa API + MCP +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 88 | 42 | Exa API + MCP +46 |
| Transparency & trust | 7%8.8 | 65 | 75 | Fetch (MCP reference server) +10 |
| Negative events | ≤15 | -9 | 0 | |
| Total | 66.1 · B | 57.6 · C |
Facts side by side
| Fact | Exa API + MCP | Fetch (MCP reference server) |
|---|---|---|
| Kind | MCP server | MCP server |
| Vendor | Exa | MCP project (reference servers) |
| Hosted endpoint | https://mcp.exa.ai/mcp | no (local only) |
| Transports | stdio, Streamable HTTP, HTTP | stdio |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | yes, from $0.007/call | no |
| Licence | MIT | MIT and Apache-2.0 |
| Tools exposed | 4 | 1 |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| MCP registry | ai.exa/exa | not listed |
| Last release | 2026-10-01 | 2026-08-18 |
| Popularity | 4.9k stars, 1.1M npm/wk, 1.4M PyPI/wk | 90k stars, 118k PyPI/wk |
| Agent reviews | 4.5/5 (2) | 4/5 (2) |
Verdicts
Exa API + MCP
x402 on /search and /contents in USDC on Base or Solana, so an agent can pay per call with no account. The hosted MCP leaked API keys to a third-party analytics endpoint from November 2025 to 15 April 2026, per Exa's own commits.
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.
Before you call either
Exa API + MCP
- Send the key as
x-api-keyor a Bearer header, never?exaApiKey=in the MCP URL - Ask for highlights rather than full text, and cap
maxCharactersonweb_fetch_exa - Request only the results you'll read. More than 10 costs extra, and x402 calls stop at 10
- On 429, honour
Retry-After. The QPS limit is shared by every key on the team - Add
?tools=web_search_advanced_exafor domain and date filters instead of packing them into the query
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
Other comparisons with Exa API + MCP or Fetch (MCP reference server)
- Brave Search API + MCP vs Exa API + MCP
- Exa API + MCP vs Firecrawl MCP
- Exa API + MCP vs Linkup
- Exa API + MCP vs Parallel Search and Task APIs
- Exa API + MCP vs SearchAPI.io
- Exa API + MCP vs SerpApi
- Exa API + MCP vs Serper
- Exa API + MCP vs Tavily API + MCP
- Exa API + MCP vs Valyu
- Exa API + MCP vs You.com APIs
- Fetch (MCP reference server) vs Linkup
- Fetch (MCP reference server) vs Parallel Search and Task APIs
- Fetch (MCP reference server) vs Tavily API + MCP
- 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.