Summary
This connects Claude to Exa's neural search engine, which uses semantic understanding rather than keyword matching to find web content. The source doesn't list specific tools, but Exa typically offers search and content retrieval operations that let you ask natural language queries and get back relevant pages with full text. You'd use this when you need Claude to find recent information or domain-specific content that goes beyond its training data. It's part of the Pipeworx gateway ecosystem, so you can either connect to this single integration or access it through their unified gateway alongside 700+ other data sources. Authentication and API key details aren't provided in the documentation.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
mcp-exa
Exa MCP — neural/semantic web search + content retrieval (exa.ai)
Part of Pipeworx — an MCP gateway connecting AI agents to 1394+ live data sources.
Tools
| Tool | Description |
|---|---|
search | 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" }) |
get_contents | 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"] }) |
find_similar | 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 }) |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"exa": {
"url": "https://gateway.pipeworx.io/exa/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 1394+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Exa data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Featured
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
