MCP server

Exa

io.github.pipeworx-io/exa

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Exa MCP — neural/semantic web search + content retrieval (exa.ai)

Website Source

At a glance

Type

MCP server

Publisher

pipeworx.io (verified by the MCP Registry)

Status

Working at last check

Tools

45

Token cost

About 27,123 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http exa https://gateway.pipeworx.io/exa/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.exa]
url = "https://gateway.pipeworx.io/exa/mcp"

Gemini CLI

{"mcpServers":{"exa":{"httpUrl":"https://gateway.pipeworx.io/exa/mcp"}}}

Cursor

{"mcpServers":{"exa":{"url":"https://gateway.pipeworx.io/exa/mcp"}}}

VS Code

{"servers":{"exa":{"type":"http","url":"https://gateway.pipeworx.io/exa/mcp"}}}

Antigravity

agy mcp add exa https://gateway.pipeworx.io/exa/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"exa","server_url":"https://gateway.pipeworx.io/exa/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"exa","server_url":"https://gateway.pipeworx.io/exa/mcp"}

Tools

• find_similar ~202 tokens
  Find pages similar to a given URL using neural/semantic matching. Returns title, URL, relevance score, and published date. Example: find_similar({ url: "https://example.com/great-article", num_results: 10 })
• get_contents ~196 tokens
  Retrieve clean, parsed page contents (text) for one or more Exa result IDs or URLs. Use after search to read the full content of pages. Example: get_contents({ ids: ["https://example.com/article"] })
• search ~422 tokens
  Neural/semantic web search — find pages by meaning, not just keywords. Returns title, URL, published date, author, and relevance score. Optionally retrieve clean page text inline. Example: search({ query: "startups building AI agents for customer support", num_results: 10, type: "neural" })

Browse

• GitHub tools
• Exa tools
• Web search
• GitHub and code hosting

Related MCP servers

• JYOTINT Sealed Forecasts
  Bitcoin-anchored sealed-forecast record: search, grades, calibration, luck test. Read-only, no key.
• Robotbase Content
  Agent MCP: 35 tools — social hot lists, attention trends, 80k+ books, 17 web tools.
• Apple-rag
  Apple developer docs and WWDC transcripts with RAG retrieval and Jev relevance ranking.
• Handover
  Shared, versioned context that humans and AI agents can publish, review, annotate, and continue.
• Context Link
  One semantic search across your sites, Drive, Notion, email, files and Basecamp.
• Gnosem
  Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
• KG Agent Exchange
  Remote MCP to publish, search, and get information. x402 v2 required.
• Diogenes Autonomous Microservice Gateway
  Autonomous AI microservices: 55 dynamic guardrails, contract audits & oracles via L402/x402/MPP.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.pipeworx-io/exa.svg)](https://aptlynx.net/servers/io.github.pipeworx-io/exa)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents