How do I use Exa MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Exa MCP Server search for latest AI developments in 2024" 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.

Exa MCP Server

by joerup

Overview Schema Related Servers Score Discussions

TypeScript

Hybrid

Exa MCP Server 🔍

npm version

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.

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?exaApiKey=your-exa-api-key

Replace your-api-key-here with your actual Exa API key from dashboard.exa.ai/api-keys.

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?exaApiKey=your-exa-api-key"
      ]
    }
  }
}

NPM Installation

npm install -g exa-mcp-server

Using Claude Code

claude mcp add exa -e EXA_API_KEY=YOUR_API_KEY -- npx -y exa-mcp-server

Using Smithery

To install the Exa MCP server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install exa --client claude

Related MCP server: 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", "exa-mcp-server"],
      "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.

3. Available Tools & Tool Selection

The Exa MCP server includes the following tools, which can be enabled by adding the --tools:

web_search_exa: Performs real-time web searches with optimized results and content extraction.
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.

You can choose which tools to enable by adding the --tools parameter to your Claude Desktop configuration:

Specify which tools to enable:

{
  "mcpServers": {
    "exa": {
      "command": "npx",
      "args": [
        "-y",
        "exa-mcp-server",
        "--tools=web_search_exa,company_research,crawling,linkedin_search,deep_researcher_start,deep_researcher_check"
      ],
      "env": {
        "EXA_API_KEY": "your-api-key-here"
      }
    }
  }
}

For enabling multiple tools, use a comma-separated list:

{
  "mcpServers": {
    "exa": {
      "command": "npx",
      "args": [
        "-y",
        "exa-mcp-server",
        "--tools=web_search_exa,company_research,crawling,linkedin_search,deep_researcher_start,deep_researcher_check"
      ],
      "env": {
        "EXA_API_KEY": "your-api-key-here"
      }
    }
  }
}

If you don't specify any tools, all tools enabled by default will be used.

4. Restart Claude Desktop

For the changes to take effect:

Completely quit Claude Desktop (not just close the window)
Start Claude Desktop again
Look for the icon to verify the Exa server is connected

Using via NPX

If you prefer to run the server directly, you can use npx:

# Run with all tools enabled by default
npx exa-mcp-server

# Enable specific tools only
npx exa-mcp-server --tools=web_search_exa

# Enable multiple tools
npx exa-mcp-server --tools=web_search_exa,company_research

# List all available tools
npx exa-mcp-server --list-tools

Troubleshooting 🔧

Common Issues

Server Not Found
- Verify the npm link is correctly set up
- Check Claude Desktop configuration syntax (json file)
API Key Issues
- Confirm your EXA_API_KEY is valid
- Check the EXA_API_KEY is correctly set in the Claude Desktop config
- Verify no spaces or quotes around the API key
Connection Issues
- Restart Claude Desktop completely
- Check Claude Desktop logs:

Built with ❤️ by team Exa

Available Tools

2 tools

get_code_context_exaA

Read-onlyIdempotent

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.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	Search query to find relevant context for APIs, Libraries, and SDKs. For example, 'React useState hook examples', 'Python pandas dataframe filtering', 'Express.js middleware', 'Next js partial prerendering configuration'
`tokensNum`	No	Number of tokens to return (1000-50000). Default is 5000 tokens. Adjust this value based on how much context you need - use lower values for focused queries and higher values for comprehensive documentation.

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe, repeatable read operation. The description adds some behavioral context by mentioning 'highest quality and freshest context' and the mandatory usage rule, but doesn't provide additional details about rate limits, authentication needs, or specific output characteristics beyond what annotations cover.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized with three sentences that each serve a distinct purpose: stating the tool's purpose, highlighting its quality/freshness, and providing usage rules. It's front-loaded with the core functionality. While efficient, the third sentence could be slightly more concise by combining the two usage guidelines.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (2 parameters, 100% schema coverage), good annotations covering safety profile, and no output schema, the description provides sufficient context. It clearly defines purpose, usage boundaries, and quality characteristics. The main gap is lack of output format information, but with annotations indicating it's read-only/idempotent, completeness is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents both parameters (query and tokensNum). The description doesn't add any meaningful parameter semantics beyond what's in the schema - it mentions 'search query' generically but provides no additional syntax, format, or usage details for parameters. Baseline 3 is appropriate when schema does all the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search and get relevant context for any programming task' with specific resources mentioned ('libraries, SDKs, and APIs'). It distinguishes from the sibling tool 'web_search_exa' by specifying 'Exa-code has the highest quality and freshest context for libraries, SDKs, and APIs' and limiting to programming-related queries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidelines: 'Use this tool for ANY question or task related to programming' and includes a rule: 'when the user's query contains exa-code or anything related to code, you MUST use this tool.' This clearly defines when to use this tool versus alternatives like the general web_search_exa sibling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

web_search_exaA

Read-onlyIdempotent

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.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	Websearch query
`numResults`	No	Number of search results to return (default: 8)
`livecrawl`	No	Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback')
`type`	No	Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search
`contextMaxCharacters`	No	Maximum characters for context string optimized for LLMs (default: 10000)

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond this: it mentions 'real-time web searches,' 'scrape content,' and 'returns the content from the most relevant websites,' which clarifies the tool's operational behavior and output format. No contradiction with annotations exists, and the added details enhance understanding of the tool's actions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded, with a clear main purpose stated first ('Search the web using Exa AI'), followed by key features in a single, efficient sentence. Every phrase adds value without redundancy, making it easy to grasp the tool's core functionality quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (5 parameters, 100% schema coverage, annotations provided, no output schema), the description is reasonably complete. It covers the tool's purpose, key behaviors, and output intent. However, without an output schema, it could benefit from more detail on the structure of returned content (e.g., format, fields) to fully compensate, slightly limiting completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, meaning all parameters are well-documented in the schema itself. The description adds minimal semantic value beyond the schema, only implying result counts and content return through phrases like 'configurable result counts' and 'returns the content.' This meets the baseline for high schema coverage, but doesn't significantly enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Search the web using Exa AI - performs real-time web searches and can scrape content from specific URLs.' It specifies the verb (search/scrape) and resource (web/URLs). However, it doesn't explicitly differentiate from its sibling 'get_code_context_exa' which might have overlapping search functionality, preventing a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context through phrases like 'real-time web searches' and 'scrape content from specific URLs,' suggesting when this tool is appropriate. However, it lacks explicit guidance on when to use this versus the sibling tool 'get_code_context_exa' or any alternatives, and doesn't specify exclusions or prerequisites, leaving room for ambiguity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

7 tool updatesv1.0.0Jan 3, 2026

Removedcompany_research_exa
Removedcrawling_exa
Removeddeep_researcher_check
Removeddeep_researcher_start
Addedget_code_context_exa
Removedlinkedin_search_exa

Changedweb_search_exa5 fields changed

addedInput schema / properties / contextMaxCharacters

Added value: +{
+  "description": "Maximum characters for context string optimized for LLMs (default: 10000)",
+  "type": "number"
+}

addedInput schema / properties / livecrawl

Added value: +{
+  "description": "Live crawl mode - 'fallback': use live crawling as backup if cached content unavailable, 'preferred': prioritize live crawling (default: 'fallback')",
+  "enum": [
+    "fallback",
+    "preferred"
+  ],
+  "type": "string"
+}

changedInput schema / properties / numResults / description

Previous value: -"Number of search results to return (default: 5)"New value: +"Number of search results to return (default: 8)"

changedInput schema / properties / query / description

Previous value: -"Search query"New value: +"Websearch query"

addedInput schema / properties / type

Added value: +{
+  "description": "Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search",
+  "enum": [
+    "auto",
+    "fast",
+    "deep"
+  ],
+  "type": "string"
+}

6 tool updatesAug 22, 2025
- First observedcompany_research_exa
- First observedcrawling_exa
- First observeddeep_researcher_check
- First observeddeep_researcher_start
- First observedlinkedin_search_exa
- First observedweb_search_exa

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Disambiguation5/5

The two tools have clearly distinct purposes: one is specialized for programming-related searches (code context, libraries, SDKs, APIs), while the other is for general web searches and URL scraping. There is no overlap in functionality, making it easy for an agent to choose the correct tool based on the query content.

Naming Consistency5/5

Both tools follow a consistent naming pattern: they use snake_case and include 'exa' as a suffix (get_code_context_exa, web_search_exa). The verbs 'get' and 'search' are appropriate and distinct, and the naming structure is predictable across the tool set.

Tool Count3/5

With only 2 tools, the server feels thin for a general-purpose search domain, as it might lack coverage for other potential use cases like news, images, or specialized data queries. However, the tools are well-scoped for code and web searches, so it's borderline but not severely mismatched.

Completeness4/5

The tools cover core search functionalities for programming and general web content, with no dead ends. A minor gap exists in not having tools for other search types (e.g., image search or advanced filtering), but agents can likely work around this by using the provided tools effectively.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

seltz-ai-seltz-mcpOAuth
ai.seltz
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
Search Browser Automation Web Scraping
2
Searchapi AOAuth
io.searchapi
Give AI assistants access to real-time data. Search the web, compare flights, find hotels, and more.
Search Browser Automation Travel & Transportation
6
Ninelayer
in.ninelayer
Agent-native search engine with live web research optimized for AI agents.
Search Agent Orchestration
2
Nimrod ResearchOAuth
ai.orchis
Web research for agents: quality-scored Google search, webpage extraction, and deep research.
Browser Automation Search Web Scraping
1256

Related MCP Servers

Exa MCP Server
Search Browser Automation Research & Data
meicanhong
A
license
Not graded
quality
C
maintenance
Enables AI assistants to perform web searches, research paper searches, and Twitter searches using the Exa AI Search API with real-time crawling and structured results.
Updated a year ago (2025-04-04 19:10 UTC)
25,462
MIT
Exa MCP Server
Search Browser Automation Research & Data
aditya002p
A
license
Not graded
quality
D
maintenance
Enables AI assistants to perform web searches, research papers, Twitter searches, company research, URL crawling, and LinkedIn searches using the Exa AI Search API for real-time web information.
Updated a year ago (2025-04-27 14:22 UTC)
25,462
1
MIT
Exa MCP Server
Search Developer Tools RAG Systems
ZooTi9er
A
license
Not graded
quality
D
maintenance
Connects AI assistants to Exa AI's search capabilities, enabling web search, company research, URL crawling, LinkedIn search, and specialized code search across GitHub repos, documentation, and Stack Overflow for finding relevant coding context and examples.
Updated a year ago (2025-09-29 15:10 UTC)
25,462
MIT
Exa MCP Server
Search RAG Systems Developer Tools
jordyvandomselaar
A
license
Not graded
quality
D
maintenance
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.
Updated 8 months ago (2026-01-05 01:31 UTC)
13
MIT

Appeared in Searches

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/joerup/exa-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server