Exa MCP Server
This Exa MCP server connects AI agents to Exa's web search, crawling, and research capabilities.
Search the web in real time with configurable result counts, search depth, live crawling, and LLM-friendly context limits.
Run natural-language deep searches for specific information with optional keyword queries.
Research companies for business, financial, news, and industry insights.
Crawl specific URLs to extract full text, metadata, and structured page content.
Search LinkedIn profiles, companies, and professional content.
Start and poll AI-powered deep research tasks that produce detailed, sourced reports.
Retrieve relevant context for programming tasks, including APIs, libraries, SDKs, and documentation.
Use the hosted Exa MCP endpoint anonymously with rate limits, or authenticate via OAuth/API key for higher limits and advanced features.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Exa MCP Server search for the latest React documentation on hooks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Installation
Connect to Exa's hosted MCP server:
https://mcp.exa.ai/mcpOr 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-officialCodex / ChatGPT
Install via Plugins in ChatGPT, or run:
codex mcp add exa --url https://mcp.exa.ai/mcpOther MCP Clients
Most clients can be configured manually with the standard mcpServers shape:
{
"mcpServers": {
"exa": {
"type": "streamable-http",
"url": "https://mcp.exa.ai/mcp",
}
}
}Exa MCP works with most other clients, point them at https://mcp.exa.ai/mcp.
Client | Where to add it |
Kiro | Use the Kiro power, or add manually to |
LM Studio | Add to LM Studio, or add manually to |
Replit | |
Grok Build |
|
Gemini CLI | Add manually to |
OpenCode | Add manually to |
Windsurf | Add manually to |
Google Antigravity | Add manually to |
Zed | Add manually to |
Warp | |
v0 by Vercel |
Related MCP server: Exa MCP Server
Available Tools
Default Tools
Tool | Description |
| Search the web for any topic and get clean, ready-to-use content |
| Read a webpage's full content as clean markdown from one or more URLs |
Optional Tools (enable via the tools parameter)
Tool | Description |
| Run an Exa Agent for multi-step research, list-building, enrichment, and structured output |
| Advanced 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_runExa Agent requires authentication (OAuth or an API key).
Dynamic Highlights (beta)
Add dynamicHighlights=true to the MCP URL to make web_search_exa and web_search_advanced_exa return Dynamic Highlights. These are highlights chosen across all results under one shared budget, not a fixed budget per URL, so less text reaches your agent's context. When the server runs locally, set DYNAMIC_HIGHLIGHTS=true instead.
https://mcp.exa.ai/mcp?dynamicHighlights=trueAgent Skills
Skills live in skills/ and load with Agent Plugin installs. The Claude plugin in plugins/exa/ ships a copy of them; npm test fails when the copy drifts. Each package version bump on main publishes plugins/exa/ to the root of the claude-plugin branch, which Claude's plugin directory reads. To publish a plugin-only change between releases, run the Publish Claude plugin workflow manually.
Skill | Path | Use when |
| Current facts, external sources, a supplied URL, people, companies, news or publications | |
| 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
Available Tools
8 toolscompany_research_exaCInspect
Research companies using Exa AI - finds comprehensive information about businesses, organizations, and corporations. Provides insights into company operations, news, financial information, and industry analysis.
Inputs: companyName (required), numResults.
crawling_exaBInspect
Extract and crawl content from specific URLs using Exa AI - retrieves full text content, metadata, and structured information from web pages. Ideal for extracting detailed content from known URLs.
Inputs: url (required), maxCharacters.
deep_researcher_checkAInspect
Check the status and retrieve results of a deep research task. This tool monitors the progress of an AI agent that performs comprehensive web searches, analyzes multiple sources, and synthesizes findings into detailed research reports. The tool includes a built-in 5-second delay before checking to allow processing time. IMPORTANT: You must call this tool repeatedly (poll) until the status becomes 'completed' to get the final research results. When status is 'running', wait a few seconds and call this tool again with the same task ID.
Inputs: taskId (required).
deep_researcher_startAInspect
Start a comprehensive AI-powered deep research task for complex queries. This tool initiates an intelligent agent that performs extensive web searches, crawls relevant pages, analyzes information, and synthesizes findings into a detailed research report. The agent thinks critically about the research topic and provides thorough, well-sourced answers. Use this for complex research questions that require in-depth analysis rather than simple searches. After starting a research task, IMMEDIATELY use deep_researcher_check with the returned task ID to monitor progress and retrieve results.
Inputs: instructions (required), model.
deep_search_exaBRead-onlyIdempotentInspect
Searches the web and return results in a natural language format.
Inputs: objective (required), search_queries.
get_code_context_exaARead-onlyIdempotentInspect
Search and get relevant context for any programming task. Exa-code has the highest quality and freshest context for libraries, SDKs, and APIs. Use this tool for ANY question or task for related to programming. RULE: when the user's query contains exa-code or anything related to code, you MUST use this tool.
Inputs: query (required), tokensNum.
linkedin_search_exaBInspect
Search LinkedIn profiles and companies using Exa AI - finds professional profiles, company pages, and business-related content on LinkedIn. Useful for networking, recruitment, and business research.
Inputs: query (required), searchType, numResults.
web_search_exaARead-onlyIdempotentInspect
Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs. Supports configurable result counts and returns the content from the most relevant websites.
Inputs: query (required), numResults, livecrawl, type, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
The tools have overlapping purposes that could cause confusion. For example, web_search_exa and deep_search_exa both perform web searches, with the latter adding natural language formatting, while crawling_exa and web_search_exa both handle URL content extraction. However, descriptions help differentiate some specialized tools like get_code_context_exa and linkedin_search_exa.
Most tools follow a consistent snake_case pattern with a '_exa' suffix, such as company_research_exa and web_search_exa. The main deviation is deep_researcher_start and deep_researcher_check, which use a different naming style without the suffix, slightly breaking the pattern.
With 8 tools, the count is well-scoped for a server focused on web research and data extraction. Each tool serves a distinct function within this domain, such as company research, LinkedIn searches, and code context retrieval, making the set appropriately sized.
The toolset covers core research workflows, including starting and checking deep research tasks, general and specialized searches, and content extraction. A minor gap exists in lacking explicit update or delete operations for research tasks, but agents can work around this by managing task IDs and polling.
Maintenance
Related MCP Connectors
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Web search API and MCP server for developers building AI agents.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Exa MCP — neural/semantic web search + content retrieval (exa.ai)
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables Claude to perform web research by integrating Google search, extracting webpage content, and capturing screenshots.320MIT
- FlicenseAqualityDmaintenanceA Model Context Protocol server that enables AI assistants like Claude to perform real-time web searches using the Exa AI Search API in a safe and controlled manner.2-
- AlicenseAqualityDmaintenanceA server that enables AI assistants like Claude to perform web searches using the Exa AI Search API, providing real-time web information in a safe and controlled way.2MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables AI assistants to perform real-time web searches, retrieving up-to-date information from the internet via a Crawler API.155 npm42ISC