Exa MCP Server

Connect AI agents to Exa for web search, content fetching, and multi-step research. Its 4 documented tools cover web, exa. It is available as a remote MCP endpoint.

Teams that want a hosted web scraping endpoint instead of running a local process. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-21 · ★ 4,917 · #9 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25

MIT · TypeScript servers · how we verify → /methodology

01 · Install Exa

Claude Code

claude mcp add exa-labs-exa-mcp-server --transport http https://mcp.exa.ai/mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "exa-labs-exa-mcp-server": {
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://mcp.exa.ai/mcp

transport: streamable-http

endpoint alive - responded to MCP initialize · probed 2026-08-25

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as remote - your agent's requests go to mcp.exa.ai

endpoint auth accepted our unauthenticated MCP initialize - no credentials needed to connect

license MIT - declared in the repository

registry vendor namespace ai.exa - domain-verified with the official MCP registry

03 · What Exa can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can 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, and run an Exa Agent for multi-step research, list-building, enrichment, and structured output.

Capability map

Tools grouped from the project's README - what Exa lets an agent do.

Web

3 tools - e.g. 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; Advanced search with filters, domains, dates, highlights…

web_search_exa · web_fetch_exa · web_search_advanced_exa

Agent

1 tool - e.g. Run an Exa Agent for multi-step research, list-building, enrichment, and structured output

agent_run

In the wild · how people use Exa

Public posts that name a concrete use case. Linked source posts - not MCPhq reviews, ratings, or endorsements.

04 · Who maintains Exa

exa is maintained by exa-labs. We track 2 MCP servers from exa-labs - 1 actively maintained, 4,917 combined GitHub stars, oldest repo from Nov 2024.

05 · Facts

repository
github.com/exa-labs/exa-mcp-server
category
web scraping - ranked #9 of 78 actively-maintained web scraping servers as of 2026-08-25.
registry
ai.exa/exa (active, first published 2025-10-30 · 6 versions)

06 · Exa FAQ

Is Exa still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-21. We re-verify nightly.

What can Exa do?

With this server connected, an agent can 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, and run an Exa Agent for multi-step research, list-building, enrichment, and structured output.

How do I install Exa?

Run `claude mcp add exa-labs-exa-mcp-server --transport http https://mcp.exa.ai/mcp`. You can also paste the ready-made client config above.

Does Exa require authentication?

No - the endpoint accepted our unauthenticated MCP initialize when probed on 2026-08-25; you can connect without credentials.

07 · Alternatives to Exa

Alternatives to Exa

Maintained web scraping servers if Exa isn't the fit.

  1. Firecrawl MCP Server MCP server for Firecrawl - web search, scraping, and biomedical/arXiv paper search. ★ 7,310 · 2026-08-25
  2. Apify MCP Server Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡ ★ 4,718 · 2026-08-23
  3. Wigolo Local-first web intelligence MCP server for AI coding agents ★ 4,647 · 2026-08-24
  4. Tavily MCP MCP server for advanced web search using Tavily ★ 2,351 · 2026-08-20
  5. Open Brand Extract brand assets (logos, colors, backdrop images, brand name) from any website URL ★ 785 · 2026-05-12
  6. Omnisearch MCP server for integrating Omnisearch with LLMs ★ 345 · 2026-08-21

Pairs well with

Servers that cover what Exa doesn't - only shown when the pairing reason fits the companion.

  1. SearXNG Search → search companion search · ★ 1,158
  2. Blockrun MCP → search companion search · ★ 388
  3. Supabase → database companion database · ★ 2,871
  4. MongoDB MCP Server → database companion database · ★ 1,106
  5. Codebase Memory → memory companion memory · ★ 40,198
  6. Memorix → memory companion memory · ★ 688

More web scraping MCP servers · Fouradata MCP Server · Glim Sh · Gmapsscraper MCP Server · CN Scraper MCP

More TypeScript MCP servers · Agent Comms · Ordinals · Yieldagentx402 · Nuxt I18n MCP · Workix · see all