Sandbox
@exa-labs/exa-mcp-server

MCP server for Exa web search and crawling

Exa MCP Server connects agent clients to Exa’s web search, page fetching, and multi-step research tools through MCP. It can be used as a hosted endpoint or installed as a plugin, with extra skills for search workflows and Exa Agent runs.

4,990 stars387 forksTypeScriptUpdated 27d ago
Who it's for

People who want their agent to search the web, read pages, and do research without leaving the client.

What it delivers

You can ask your agent to search, fetch, and research on the web without building a separate browser workflow.

What it does

Web search tool

`web_search_exa` searches the web and returns clean content for an agent to use.

Web fetch tool

`web_fetch_exa` reads full webpage content as markdown from one or more URLs.

Advanced search option

`web_search_advanced_exa` adds filters, domains, dates, highlights, summaries, and subpage crawling.

Exa Agent runs

`agent_run` lets the client run multi-step research, enrichment, list building, and structured output.

Skill packs

`skills/search/` and `skills/exa-agent/` add guided workflows on top of the MCP tools.

Plugin and MCP manifests

Files like `plugin.json`, `.claude-plugin/`, `mcp.json`, and `gemini-extension.json` make it installable across clients.

How to get it

  1. 1Connect to Exa's hosted MCP server
    https://mcp.exa.ai/mcp
  2. 2Install from the Claude Plugin Marketplace, or run
    claude plugin install exa@claude-plugins-official
  3. 3Install via Plugins in ChatGPT, or run
    codex mcp add exa --url https://mcp.exa.ai/mcp

README

Exa
Exa MCP Server

Connect AI agents to Exa for web search, content fetching, and multi-step research.

Install in Cursor Install in VS Code Install Claude Plugin Install Codex/ChatGPT Plugin

Documentation  ·  NPM Package  ·  Get your API key

Installation

Connect to Exa's hosted MCP server:

https://mcp.exa.ai/mcp

Or use a plugin when your client supports one.

Agent Plugin

This repository is an Agent Plugin. Install it with any compatible client.

Claude

Install from the Claude Plugin Marketplace, or run:

claude plugin install exa@claude-plugins-official

Codex / ChatGPT

Install via Plugins in ChatGPT, or run:

codex mcp add exa --url https://mcp.exa.ai/mcp

Other MCP Clients

Most clients can be configured manually with the standard mcpServers shape:

{
  "mcpServers": {
    "exa": {
      "type": "streamable-http",
      "url": "https://mcp.exa.ai/mcp",
    }
  }
}
Client-specific configs

Exa MCP works with most other clients, point them at https://mcp.exa.ai/mcp.

ClientWhere to add it
KiroUse the Kiro power, or add manually to ~/.kiro/settings/mcp.json
LM StudioAdd to LM Studio, or add manually to mcp.json
ReplitAdd to Replit
Grok Build/marketplace → install Exa, then /mcp to sign in
Gemini CLIAdd manually to ~/.gemini/settings.json
OpenCodeAdd manually to opencode.json
WindsurfAdd manually to ~/.codeium/windsurf/mcp_config.json
Google AntigravityAdd manually to mcp_config.json
ZedAdd manually to settings.json under context_servers
WarpSettings → Agents → MCP servers
v0 by VercelSettings → MCP connections

Available Tools

Default Tools

ToolDescription
web_search_exaSearch the web for any topic and get clean, ready-to-use content
web_fetch_exaRead a webpage's full content as clean markdown from one or more URLs

Optional Tools (enable via the tools parameter)

ToolDescription
agent_runRun an Exa Agent for multi-step research, list-building, enrichment, and structured output
web_search_advanced_exaAdvanced search with filters, domains, dates, highlights, summaries, and subpage crawling

Enable tools by appending them to the MCP URL (this will replace the defaults, so include all you want):

https://mcp.exa.ai/mcp?tools=web_search_advanced_exa
https://mcp.exa.ai/mcp?tools=web_search_exa,web_fetch_exa,agent_run

Exa Agent requires authentication (OAuth or an API key).

Agent Skills

Skills live in skills/ and load with Agent Plugin / Claude plugin installs.

SkillPathUse when
searchskills/search/Deep research, lead gen, competitive analysis, multi-step web investigation
exa-agentskills/exa-agent/Exa Agent runs, enrichment, structured output, Connect providers

Invoke from your client's skill UI (or /skill-name where supported). MCP-only setups still get the tools; skills add orchestration on top.

Authentication

The hosted MCP server works anonymously with rate limits. For higher limits and access to Exa Agent, use either OAuth or an API key.

OAuth is preferred: most clients prompt you to sign in to Exa. To force the login flow (useful for shared connectors and plugins), use https://mcp.exa.ai/mcp?login or https://mcp.exa.ai/mcp/oauth.

If you prefer, you can get an API key from the dashboard and pass it on the URL as ?exaApiKey=…. You can also send it as a Authorization: Bearer … header or an x-api-key header.

Built with ❤️ by Exa

Files in the repo

Repository payload26 top-level entries
  • .claude-plugin
  • .github
  • api
  • assets
  • skills
  • src
  • tests
  • .gitignore
  • .npmignore
  • .prettierignore
  • .prettierrc.json
  • .vercelignore
  • Dockerfile
  • env.example
  • gemini-extension.json
  • LICENSE
  • mcp.json
  • package-lock.json
  • package.json
  • plugin.json
  • README.md
  • server.json
  • tsconfig.json
  • tsconfig.test.json
  • vercel.json
  • vitest.config.ts

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k