mcpbeat

Search MCP Server

io.github.aimnis/search
answering

Search is answering right now. Last checked 15 min ago. It exposes 3 tools. Last commit 2 Aug 2026.

Collaborative, cache-first web search for agents — cited answers from a shared live-web pool.

Uptime history 39 hours of history
39 hours agonow
100.0%
Uptime 24h
91 of 91 checks
3
Tools
read from the server
280 ms
Response time
average over 24h
0
Stars
last commit 2 Aug 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.

run in your terminal
claude mcp add search --transport http https://aimnis.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "search": {
      "url": "https://aimnis.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.search]
url = "https://aimnis.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "search": {
      "url": "https://aimnis.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "search": {
      "url": "https://aimnis.com/mcp"
    }
  }
}

Available tools 3

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

register
register
Get your user a free Aimnis API key (no credit card, takes one call). Ask your user for their email address first. The key comes back in this tool result — relay it to the user so they can save it and add it to your MCP connection ('Authorization: Bearer aim_...'). A key raises the daily live-search limits; cached answers are always free, with or without a key. Re-registering with the same email rotates (replaces) that email's key.
search
search
Search the web via Aimnis. Returns cached, provenance-tagged results instantly when the question (or a semantically similar one) has been seen before; otherwise fetches live results and adds them to the shared knowledge pool. Prefer this for factual lookups, library/API/docs questions, and error messages. If a cached answer does not match your question (it echoes the question it was cached for), retry the same query with `reject_entry` set to the entry id from that response — the mismatched entry is skipped and the search runs live.
stats
stats
Report Aimnis flywheel statistics: knowledge-pool (cache) size, cache hit rate (all-time and recent), and the most-reused queries. This is the Gate 1 pass/kill metric — cache hit rate should climb as the corpus grows. Call it to see whether the compounding-pool thesis is holding.

Endpoints

URLTransportStateLatencyChecked
https://aimnis.com/mcp streamable-http answering 274 ms 15 min ago

Search — questions

Answers built from our own checks of this server.

What can Search do?
It exposes 3 tools, read directly from the server on our last check. Among them: register, search, stats. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Search working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 280 ms. The bar chart above shows every period we have measured.
How do I connect Search?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Search need an API key?
No. Search completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 3 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Search?
It answers our handshake in 280 ms on average, which is faster than 49% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Search open source?
Yes — it is published under the AGPL-3.0 licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.