Andi Search MCP Server

by andiai Your server? Claim it

answering

Andi Search is answering right now. Last checked 7 min ago.

Real-time web search and page fetch for AI agents from Andi's own index. LLM-ready markdown output.

Uptime history 18 days of history · worst day 98%

18 days agonow

98.9%

Uptime 24h

90 of 91 checks

—

Tools

hidden behind auth

795 ms

Response time

average over 24h

API key or OAuth

Access

streamable-http

Andi Search does not always answer

Over the last week it answered 99.8% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add andi-search --transport http https://api.andiai.com/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "andi-search": {
      "url": "https://api.andiai.com/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.andi-search]
url = "https://api.andiai.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "andi-search": {
      "url": "https://api.andiai.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "andi-search": {
      "url": "https://api.andiai.com/mcp"
    }
  }
}

This endpoint answered with an authorization challenge — the server is running, but you need an API key or OAuth to use it.

Endpoints

URL	Transport	State	Latency	Checked
https://api.andiai.com/mcp	streamable-http	needs key	821 ms	7 min ago

Alternatives to Andi Search

same job, measured the same way

Sofya

by sofya

Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.

4 tools answering

Web Search

by keenable

Live web search and clean-markdown page fetch over the Keenable web index.

85 installs/wk 2 tools answering

Web Search

by hec-ovi

Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.

357 installs/wk local only

Agentsearch MCP

by isaiahdupree

LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.

3 tools answering

SearchForge

by divyanshu-iitian

Free open-source web search and page reading for LLMs, AI agents, and RAG.

local only

Linkup

by mcparmory

Search the web and fetch pages with sourced results, optimized for AI agents

300 installs/wk local only

by neurobird

Web search for AI agents. Ranked results with page passages already extracted, plus URL to markdown.

2 tools answering

Web Search API for all your agents and LLMs

by blopus

Live web search, image search, topic filters and full-text fetch over our own crawled index.

answering

Andi Search — questions

Answers built from our own checks of this server.

Why is there no tool list for Andi Search?

The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 98.9% of checks in the last 24 hours got a reply.

Is Andi Search working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 90 of 91 checks got a reply (98.9%), average response time 795 ms. The bar chart above shows every period we have measured.

How do I connect Andi 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. You will need your own key or an OAuth login: it refuses anonymous clients.

Does Andi Search need an API key?

Yes. Every time we knock, Andi Search answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.

How fast is Andi Search?

It answers our handshake in 795 ms on average, which is faster than 17% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.