Mcp Exa

daedalus/mcp-exa

This server connects Claude to Exa's search API without requiring your own API key, which is its main appeal. You get four tools: basic web search, code-specific search that pulls from GitHub and Stack Overflow, URL crawling for full page content, and advanced search with filters. It's a Python package you install via pip and run as a standalone command. Useful when you need Claude to search the web or fetch fresh content during a conversation, especially if you don't want to manage another API key. The code search tool is handy for finding examples when you're stuck on implementation details.

tools: 2
transport: STDIO
last updated: Mar 31, 2026

View on GitHub

Tools

2 tools

Public tool metadata for what this MCP can expose to an agent.

web_search_exaSearch the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywor...2 params

Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywor...

Parameters* required

numResultsnumber

Number of search results to return (default: 10).

querystring

Natural language search query. Should be a semantically rich description of the ideal page, not just keywords. Optionally include category:<type> (company, people) to focus results — e.g. 'category...

web_fetch_exaRead a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).2 params

Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).

Parameters* required

maxCharactersnumber

Maximum characters to extract per page (default: 3000)

urlsarray

URLs to read. Batch multiple URLs in one call.

Readme

MCP Exa

A Python MCP server that exposes Exa search capabilities (no API key required)

mcp-name: io.github.daedalus/mcp-exa

Install

pip install mcp-exa

Usage

No API key required. The server uses Exa's public MCP endpoint.

Run the MCP server:

mcp-exa

Or use as a module:

python -m mcp_exa

Configuration

Available Tools

The server exposes the following MCP tools:

Tool	Description
`web_search_exa`	Search the web for any topic
`get_code_context_exa`	Find code examples from GitHub, Stack Overflow
`crawling_exa`	Get full content from a specific URL
`web_search_advanced_exa`	Advanced search with filters

View the full README on GitHub

Details

Repository: github.com/daedalus/mcp-exa
Category: Search & Web Crawling
Package: mcp-exa
Transport: STDIO
Registry: MCP registry, active

Related Search & Web Crawling MCP servers

View all

Parallel Search MCPparallel-web/search-mcpThe best web search for your AI Agent0stars

Jina AI Remotejina-ai/mcpOfficial Jina AI Remote MCP Server680stars

code-indexregsorm/code-index-mcpRust code index MCP server, native 1C:Enterprise (BSL) support. 37 tools, AST for 14 languages.161stars

Mcp Codebase Indexmikerecognex/mcp-codebase-indexStructural codebase indexer with 17 query tools. 87% token reduction. Zero dependencies.56stars

Adamamer20 Paper Search Mcp Openaiadamamer20/paper-search-mcp-openaiSearch and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic…13stars

TranscriptAPI: YouTube Transcript and Search MCPzeropointrepo/youtube-mcpTranscriptAPI.com: hosted YouTube transcripts, search, channels and playlists for AI agents13stars