Exa MCP Server
Connects AI assistants to Exa AI's search capabilities for web search, code context retrieval from GitHub repos and documentation, company research, LinkedIn search, and deep research tasks.
README
This is a fork of https://github.com/exa-labs/exa-mcp-server.
Exa MCP Server 🔍
Exa Code: fast, efficient web context for coding agents
Vibe coding should never have a bad vibe. exa-code is a huge step towards coding agents that never hallucinate.
When your coding agent makes a search query, exa-code searches over billions
of Github repos, docs pages, Stackoverflow posts, and more, to find the perfect, token-efficient context that the agent needs to code correctly. It's powered by the Exa search engine.
Examples of queries you can make with exa-code:
- use Exa search in python and make sure content is always livecrawled
- use correct syntax for vercel ai sdk to call gpt-5 nano asking it how are you
- how to set up a reproducible Nix Rust development environment
✨ Works with Cursor and Claude Code! Use the HTTP-based configuration format:
{
"mcpServers": {
"exa": {
"type": "http",
"url": "https://mcp.exa.ai/mcp",
"headers": {}
}
}
}
You can enable specific tool(s) using the tools parameter (if multiple, then with a comma-separated list):
https://mcp.exa.ai/mcp?tools=web_search_exa,get_code_context_exa
Or enable all tools:
https://mcp.exa.ai/mcp?tools=web_search_exa,deep_search_exa,get_code_context_exa,crawling_exa,company_research_exa,linkedin_search_exa,deep_researcher_start,deep_researcher_check
You may include your exa api key in the url like this:
https://mcp.exa.ai/mcp?exaApiKey=YOUREXAKEY
Note: By default, only web_search_exa and get_code_context_exa are enabled. Add other tools as needed using the tools parameter.
A Model Context Protocol (MCP) server that connects AI assistants like Claude to Exa AI's search capabilities, including web search, research tools, and our new code search feature.
Remote Exa MCP 🌐
Connect directly to Exa's hosted MCP server (instead of running it locally).
Remote Exa MCP URL
https://mcp.exa.ai/mcp
Claude Desktop Configuration for Remote MCP
Add this to your Claude Desktop configuration file:
{
"mcpServers": {
"exa": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.exa.ai/mcp"
]
}
}
}
Cursor and Claude Code Configuration for Remote MCP
For Cursor and Claude Code, use this HTTP-based configuration format:
{
"mcpServers": {
"exa": {
"type": "http",
"url": "https://mcp.exa.ai/mcp",
"headers": {}
}
}
}
Codex Configuration for Remote MCP
Open your Codex configuration file:
code ~/.codex/config.toml
Add this configuration:
[mcp_servers.exa]
command = "npx"
args = ["-y", "mcp-remote", "https://mcp.exa.ai/mcp"]
env = { EXA_API_KEY = "your-api-key-here" }
Replace your-api-key-here with your actual Exa API key from dashboard.exa.ai/api-keys.
Claude Code Plugin
The easiest way to get started with Exa in Claude Code, using plugins:
# Add the Exa marketplace
/plugin marketplace add exa-labs/exa-mcp-server
# Install the plugin
/plugin install exa-mcp-server
Then set your API key:
export EXA_API_KEY="your-api-key-here"
Get your API key from dashboard.exa.ai/api-keys.
NPM Installation
npm install -g jordy-exa-mcp-server
Using Claude Code
claude mcp add exa -e EXA_API_KEY=YOUR_API_KEY -- npx -y jordy-exa-mcp-server
Configuration ⚙️
1. Configure Claude Desktop to recognize the Exa MCP server
You can find claude_desktop_config.json inside the settings of Claude Desktop app:
Open the Claude Desktop app and enable Developer Mode from the top-left menu bar.
Once enabled, open Settings (also from the top-left menu bar) and navigate to the Developer Option, where you'll find the Edit Config button. Clicking it will open the claude_desktop_config.json file, allowing you to make the necessary edits.
OR (if you want to open claude_desktop_config.json from terminal)
For macOS:
- Open your Claude Desktop configuration:
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
For Windows:
- Open your Claude Desktop configuration:
code %APPDATA%\Claude\claude_desktop_config.json
2. Add the Exa server configuration:
{
"mcpServers": {
"exa": {
"command": "npx",
"args": ["-y", "jordy-exa-mcp-server"],
"env": {
"EXA_API_KEY": "your-api-key-here",
"TOOLS": "web_search_exa,get_code_context_exa"
}
}
}
}
Replace your-api-key-here with your actual Exa API key from dashboard.exa.ai/api-keys.
The TOOLS environment variable (or ENABLED_TOOLS) is optional. If not specified, only web_search_exa and get_code_context_exa are enabled by default. Use a comma-separated list to enable specific tools.
3. Available Tools & Tool Selection
The Exa MCP server includes powerful tools for developers and researchers:
🌐 Tools
- get_code_context_exa: Search and get relevant code snippets, examples, and documentation from open source libraries, GitHub repositories, and programming frameworks. Perfect for finding up-to-date code documentation, implementation examples, API usage patterns, and best practices from real codebases.
- web_search_exa: Performs real-time web searches with optimized results and content extraction.
- deep_search_exa: Deep web search with smart query expansion and high-quality summaries for each result.
- company_research: Comprehensive company research tool that crawls company websites to gather detailed information about businesses.
- crawling: Extracts content from specific URLs, useful for reading articles, PDFs, or any web page when you have the exact URL.
- linkedin_search: Search LinkedIn for companies and people using Exa AI. Simply include company names, person names, or specific LinkedIn URLs in your query.
- deep_researcher_start: Start a smart AI researcher for complex questions. The AI will search the web, read many sources, and think deeply about your question to create a detailed research report.
- deep_researcher_check: Check if your research is ready and get the results. Use this after starting a research task to see if it's done and get your comprehensive report.
Note: By default, only web_search_exa and get_code_context_exa are enabled. You can enable additional tools using the TOOLS or ENABLED_TOOLS environment variable (see examples below).
💻 Setup for Code Search Only (Recommended for Developers)
{
"mcpServers": {
"exa": {
"command": "npx",
"args": ["-y", "jordy-exa-mcp-server"],
"env": {
"EXA_API_KEY": "your-api-key-here",
"TOOLS": "get_code_context_exa"
}
}
}
}
Enable All Tools:
You can either enable all tools or any specific tools. Use a comma-separated list in the TOOLS or ENABLED_TOOLS environment variable:
{
"mcpServers": {
"exa": {
"command": "npx",
"args": ["-y", "jordy-exa-mcp-server"],
"env": {
"EXA_API_KEY": "your-api-key-here",
"TOOLS": "web_search_exa,get_code_context_exa,crawling_exa,company_research_exa,linkedin_search_exa,deep_researcher_start,deep_researcher_check"
}
}
}
}
Environment Variables
The server supports the following environment variables:
EXA_API_KEY(required): Your Exa API key from dashboard.exa.ai/api-keysTOOLSorENABLED_TOOLS(optional): Comma-separated list of tool IDs to enable. If not specified, onlyweb_search_exaandget_code_context_exaare enabled by default.DEBUG(optional): Set totrueor1to enable debug logging
Available tool IDs:
web_search_exaget_code_context_exadeep_search_exacrawling_exacompany_research_exalinkedin_search_exadeep_researcher_startdeep_researcher_check
Using via NPX
If you prefer to run the server directly, you can use npx with environment variables:
# Run with default tools only (web_search_exa and get_code_context_exa)
EXA_API_KEY=your-api-key-here npx jordy-exa-mcp-server
# Enable specific tools only
EXA_API_KEY=your-api-key-here TOOLS=web_search_exa npx jordy-exa-mcp-server
# Enable multiple tools
EXA_API_KEY=your-api-key-here TOOLS=web_search_exa,get_code_context_exa,crawling_exa npx jordy-exa-mcp-server
# Enable all tools
EXA_API_KEY=your-api-key-here TOOLS=web_search_exa,get_code_context_exa,deep_search_exa,crawling_exa,company_research_exa,linkedin_search_exa,deep_researcher_start,deep_researcher_check npx jordy-exa-mcp-server
# With debug logging enabled
EXA_API_KEY=your-api-key-here TOOLS=web_search_exa DEBUG=true npx jordy-exa-mcp-server
Fork Changes
This fork contains the following changes from the original exa-labs/exa-mcp-server repository (all changes made after commit 75e902e0b495d94a025f68ab9c79d6e986316cf2):
Package Rename and Publishing
- Package renamed: Changed from
exa-mcp-servertojordy-exa-mcp-serverfor npm publishing - Version bump: Updated to version
3.1.4 - NPM package: Published as
jordy-exa-mcp-serveron npm - Updated all references in
package.json,server.json,gemini-extension.json, and documentation
Build System Migration
- Migrated from Smithery to Bun: Replaced Smithery CLI build system with Bun's native build system
- Build scripts updated:
- Removed
@smithery/clidependency - Changed build command from
smithery buildtobun build - Updated output directory from
.smithery/stdio/todist/ - Removed
smithery.yamlconfiguration file
- Removed
- Entry point changes:
- Modified
src/index.tsto useStdioServerTransportdirectly instead of Smithery's transport abstraction - Added direct stdio transport initialization in the main entry point
- Changed from default export function to named
createServerfunction with separatemain()entry point
- Modified
- Dockerfile updated: Migrated to use Bun runtime instead of Node.js
- Changed base image to
oven/bun:1-alpine - Updated build and runtime commands to use
buninstead ofnode - Updated dependency installation to use
bun install
- Changed base image to
Development Tooling
- Added Beads issue tracking: Integrated beads (bd) for issue tracking and project management
- Added
.beads/directory with configuration files - Created
AGENTS.mdwith agent instructions and workflow guidelines - Added
.beads/.gitignorefor beads-specific files - Configured beads metadata and interactions tracking
- Added
- Added
.gitattributes: Added Git attributes configuration file
Documentation Updates
- README improvements:
- Added fork notice at the top
- Updated all package references from
exa-mcp-servertojordy-exa-mcp-server - Enhanced environment variable documentation for tool configuration
- Updated installation instructions to reflect new package name
- Clarified tool selection and configuration options
Code Changes
- Server initialization refactoring:
- Separated server creation logic from transport initialization
- Added
parseConfig()function to handle environment variable parsing - Added
main()async function for direct execution - Improved error handling and logging
- Removed Smithery-specific code: Cleaned up all Smithery CLI dependencies and abstractions
Files Changed
- Added:
.beads/directory (config, README, metadata, interactions) - Added:
AGENTS.md,.gitattributes,bun.lock,dist/index.js - Modified:
package.json,package-lock.json,src/index.ts,README.md,Dockerfile,server.json,gemini-extension.json - Removed:
smithery.yaml
Summary Statistics
- 17 files changed: 653 insertions(+), 70 deletions(-)
- 6 commits after the base commit
Built with ❤️ by team Exa
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.