Server profile

Exa MCP Server

Exa MCP Server gives AI assistants web search and readable page retrieval, with optional advanced search and agent research tools. It supports hosted connections and a local npm package for research and coding context.

Server facts

Exa MCP Server

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
5,138
Last commit
Data as of

Tags

  • Code Search
  • Company Research
  • Exa
  • Web Content
  • Web Search

Overview

Exa MCP Server brings Exa's search and content retrieval into AI clients. The default interface exposes web search and a tool for reading full pages from known URLs. The supplied tool data describes clean text results and markdown page retrieval, including multiple URLs in a fetch request. Advanced search is available but disabled by default, adding control over filters, domains, dates, and content options. Optional Exa Agent tools cover asynchronous research, list building, enrichment, structured output, polling, result retrieval, and cancellation. This makes the integration relevant to both quick factual lookups and research workflows that require several steps.

The README emphasizes a hosted MCP endpoint and shows configurations for many editors, desktop assistants, and command-line agents. Claude Desktop also has a native connector route. Clients that need a local bridge can use mcp-remote, while the npm server package accepts an Exa API key. Additional toolsets are enabled with the endpoint's tools parameter, and the optional agent tools require OAuth or an API key. Several older tool names are retained only for backward compatibility, with newer search or fetch tools recommended instead. Included task-oriented guidance covers company research and programming questions, including query specificity and result deduplication. Users should distinguish the small default toolset from optional capabilities rather than assuming every research tool is active immediately.

Install & configure

Requirements

  • An MCP-compatible client
  • npx and an Exa API key for the local npm option
Documented launch / install command
npx -y exa-mcp-server

The command uses the README's local npm package configuration. The remote URL supports direct HTTP connections; mcp-remote is another documented route. Enable optional tools through the tools parameter.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "exa-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "exa-mcp-server"
      ],
      "env": {
        "EXA_API_KEY": "<your Exa API key>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "exa-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "exa-mcp-server"
      ],
      "env": {
        "EXA_API_KEY": "<your Exa API key>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "exa-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "exa-mcp-server"
      ],
      "env": {
        "EXA_API_KEY": "<your Exa API key>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "exa-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "exa-mcp-server"
      ],
      "env": {
        "EXA_API_KEY": "<your Exa API key>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "exa-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "exa-mcp-server"
      ],
      "env": {
        "EXA_API_KEY": "<your Exa API key>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository tool metadata and repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
web_search_exaSearch for relevant web sources and return readable result content.
web_fetch_exaRetrieve clean full-page content and metadata from one or more known URLs.
web_search_advanced_exaRun optional advanced searches with domain, date, filter, and content controls.
agent_create_runStart optional asynchronous research, enrichment, or structured-output work.
agent_wait_for_runPoll an Exa Agent run until completion or timeout.
agent_get_run_outputRead completed agent output with grounding, usage, and cost information.
agent_cancel_runCancel an agent task that is queued or running.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Search for current facts and retrieve readable source content.
  • Fetch complete pages when search snippets are insufficient.
  • Find code examples and library documentation for a programming question.
  • Research companies using optional advanced search filters.
  • Run asynchronous enrichment or structured research through Exa Agent.

Strengths

  • Keeps the default interface focused on search and page retrieval.
  • Offers advanced search and agent workflows as optional toolsets.
  • Documents hosted access, local npm execution, and many client integrations.

Limitations

  • Advanced search is not enabled by default.
  • Optional Exa Agent tools require OAuth or an API key.
  • Several older tool names are deprecated.

Frequently asked questions

The README enables web_search_exa and web_fetch_exa by default.

Enable web_search_advanced_exa through the tools parameter. It is disabled by default.

Yes. The optional Exa Agent toolset supports creating runs, waiting, retrieving output, and cancellation, with OAuth or an API key required.

Yes. The README describes a native Exa connector in Claude Desktop's connector directory.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

Tavily MCP Server

Search & Web Data

Tavily MCP Server connects AI clients to web search, page extraction, site mapping, and crawling. Run it locally with an API key or connect to the hosted service using API-key or OAuth authentication.

Firecrawl MCP Server

Search & Web Data

Firecrawl MCP connects AI agents to web search, scraping, crawling, and live browser interaction. It offers hosted access or a local server for collecting structured web context and running research tasks.

AgentQL MCP Server

Search & Web Data

AgentQL MCP Server extracts structured JSON from a web page using a natural-language description of the desired fields. It provides one focused extraction tool for MCP assistants.

Perplexity API Platform MCP Server

Search & Web Data

The Perplexity API Platform MCP Server gives assistants web search, conversational answers, research, and reasoning tools. It connects to Perplexity’s Search API and Sonar models through local stdio or an HTTP deployment.

ArXiv MCP Server

Search & Web Data

Search arXiv, download papers, and read their contents through an AI assistant. Local storage and research prompts support repeatable literature review and paper analysis.

Bright Data Web MCP

Search & Web Data

Give AI assistants live web search, page extraction, and optional browser automation through Bright Data. Tool groups also provide structured datasets, package information, and AI brand-visibility queries.

DuckDuckGo Search MCP Server

Search & Web Data

Give MCP assistants DuckDuckGo search and webpage text retrieval. It suits research workflows that need regional results, readable page content, and configurable filtering.

Yargı MCP

Search & Web Data

Search Turkish court and regulatory decisions from MCP-compatible assistants. Yargı MCP retrieves decision texts as Markdown and offers both local execution and a hosted streamable HTTP endpoint.