Click on "Install 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 find recent breakthroughs in renewable energy storage"
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.
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.
Demo video https://www.loom.com/share/ac676f29664e4c6cb33a2f0a63772038?sid=0e72619f-5bfc-415d-a705-63d326373f60
The Model Context Protocol (MCP) is a system that lets AI apps, like Claude Desktop, connect to external tools and data sources. It gives a clear and safe way for AI assistants to work with local services and APIs while keeping the user in control.
Related MCP server: Exa MCP Server
The Exa MCP server:
Enables AI assistants to perform web searches using Exa's powerful search API
Provides structured search results including titles, URLs, and content snippets
Handles rate limiting and error cases gracefully
Before you begin, ensure you have:
Node.js (v18 or higher)
Claude Desktop installed
An Exa API key
Git installed
You can verify your Node.js installation by running:
node --version # Should show v18.0.0 or highernpm install -g exa-mcp-serverTo install the Exa MCP server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install exa --client claudeClone the repository:
git clone https://github.com/exa-labs/exa-mcp-server.git
cd exa-mcp-serverInstall dependencies:
npm install --save axios dotenvBuild the project:
npm run buildCreate a global link (this makes the server executable from anywhere):
npm linkYou 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)
Open your Claude Desktop configuration:
code ~/Library/Application\ Support/Claude/claude_desktop_config.jsonOpen your Claude Desktop configuration:
code %APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"exa": {
"command": "npx",
"args": ["/path/to/exa-mcp-server/build/index.js"],
"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.
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
Once configured, you can ask Claude to perform web searches. Here are some example prompts:
Can you search for recent developments in quantum computing?Search for and summarize the latest news about artificial intelligence startups in new york.Find and analyze recent research papers about climate change solutions.The server will:
Process the search request
Query the Exa API
Return formatted results to Claude
Cache the search for future reference
Web Search Tool: Enables Claude to search the web using natural language queries
Error Handling: Gracefully handles API errors and rate limits
Type Safety: Full TypeScript implementation with proper type checking
Server Not Found
Verify the npm link is correctly set up
Check Claude Desktop configuration syntax
Ensure Node.js is properly installed
API Key Issues
Confirm your Exa API key is valid
Check the 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:
# macOS
tail -n 20 -f ~/Library/Logs/Claude/mcp*.logIf you encounter issues review the MCP Documentation
Exa AI for their powerful search API
Model Context Protocol for the MCP specification
Anthropic for Claude Desktop
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.
| 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. |
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 context about quality ('highest quality and freshest context') and scope ('for libraries, SDKs, and APIs'), but doesn't disclose behavioral traits like rate limits, authentication needs, or response format beyond what annotations provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized with three sentences that each serve a purpose: stating the tool's purpose, highlighting its quality, and providing usage rules. It's front-loaded with the core functionality, though the capitalization in 'RULE' and 'MUST' could be more polished.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
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, no output schema) and rich annotations covering safety and idempotency, the description provides adequate context. It explains when to use the tool and its programming focus, though it doesn't describe return values or error handling, which would be helpful given the lack of output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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. The description doesn't add any parameter-specific information beyond what's in the schema, maintaining the baseline score of 3 for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
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 'web_search_exa' by specifying programming-related queries, though not explicitly contrasting capabilities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage rules: 'Use this tool for ANY question or task related to programming' and 'RULE: when the user's query contains exa-code or anything related to code, you MUST use this tool.' This gives clear when-to-use guidance, though it doesn't mention when NOT to use it or explicitly compare to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| 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) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and idempotency. The description adds valuable behavioral context beyond annotations: it specifies real-time web search capability, content scraping from URLs, and configurable result handling. However, it doesn't mention rate limits, authentication needs, or error behaviors, leaving some gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured in two sentences, front-loaded with core functionality and followed by supporting features. Every sentence adds value: the first defines the tool's primary actions, and the second explains configurability and output. There is no redundant or verbose content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
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, no output schema), the description is largely complete. It covers the tool's purpose, key behaviors, and output nature ('returns the content from the most relevant websites'). However, without an output schema, it could benefit from more detail on return format (e.g., structure of results, error handling) to fully compensate for the missing structured output documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing detailed documentation for all 5 parameters. The description adds minimal semantic value beyond the schema, mentioning configurable result counts and relevance but not elaborating on parameter interactions or use cases. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't significantly enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('search the web', 'scrape content from specific URLs') and resources ('Exa AI', 'web searches', 'URLs'). It distinguishes from the sibling tool 'get_code_context_exa' by focusing on general web search rather than code-specific context, establishing a clear functional boundary.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for real-time web searches and content scraping, but provides no explicit guidance on when to use this tool versus the sibling 'get_code_context_exa' or other alternatives. It mentions configurable result counts and relevance, but lacks specific scenarios, exclusions, or comparative context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0company_research_exacrawling_exadeep_researcher_checkdeep_researcher_startget_code_context_exalinkedin_search_exaweb_search_exa5 fields changedInput schema / properties / contextMaxCharactersAdded value: +{
+ "description": "Maximum characters for context string optimized for LLMs (default: 10000)",
+ "type": "number"
+}Input schema / properties / livecrawlAdded 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"
+}Input schema / properties / numResults / descriptionPrevious value: -"Number of search results to return (default: 5)"New value: +"Number of search results to return (default: 8)"Input schema / properties / query / descriptionPrevious value: -"Search query"New value: +"Websearch query"Input schema / properties / typeAdded value: +{
+ "description": "Search type - 'auto': balanced search (default), 'fast': quick results, 'deep': comprehensive search",
+ "enum": [
+ "auto",
+ "fast",
+ "deep"
+ ],
+ "type": "string"
+}company_research_exacrawling_exadeep_researcher_checkdeep_researcher_startlinkedin_search_exaweb_search_exaThe two tools have clearly distinct purposes: get_code_context_exa is specialized for programming-related searches with high-quality code context, while web_search_exa is for general web searches and URL scraping. There is no overlap in functionality, making it easy for an agent to choose the right tool based on the query type.
Both tools follow a consistent naming pattern: they use snake_case and start with a verb (get, search) followed by a noun (code_context, web), with a suffix (_exa) indicating the server. This uniformity makes the tool set predictable and easy to understand.
With only 2 tools, the server feels thin for its apparent scope of providing search capabilities via Exa AI. While the tools cover code-specific and general web searches, the lack of additional tools (e.g., for filtering, advanced queries, or other Exa features) limits functionality and suggests an incomplete surface for a search-oriented server.
The tool set is severely incomplete for a search server. It lacks essential operations such as configuring search parameters beyond result counts, handling pagination, saving or managing search history, or accessing other Exa AI features. This creates significant gaps that could lead to agent failures when more complex search tasks are required.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
Fast, intelligent web search and web crawling. New mcp tool: Exa-code is a context tool for coding
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MrunmayS/exa-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
