Extracto MCP Server

Turn any URL plus a schema into validated, typed JSON via the Extracto API.

Local serverstdioTypeScript

What is the Extracto MCP server?

If you already use Extracto, the extracto mcp server is the piece that lets your assistant work with it directly. Turn any URL plus a schema into validated, typed JSON via the Extracto API.

What the server does

You need an Extracto API key. Get one at app.getextracto.dev/keys.

Installation

extracto-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • extract — Synchronous extraction from a single URL (up to ~90s). Returns { data, meta }
  • extract_async — Submit an async job for heavy or anti-bot pages. Returns a job id immediately
  • get_job — Poll an async job for status and result
  • list_jobs — List your recent async jobs
  • Cursor — Add to ~/.cursor/mcp.json (or the project .cursor/mcp.json) with the same block

Credentials and setup notes

Configuration is passed through the environment: EXTRACTO_API_KEY, EXTRACTO_BASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Extracto's toolset — extract, extract_async, get_job and 2 more — is a fair guide to whether it matches your workflow. It is maintained by massanaRoger; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
extractSynchronous extraction from a single URL (up to ~90s). Returns { data, meta }.
extract_asyncSubmit an async job for heavy or anti-bot pages. Returns a job id immediately.
get_jobPoll an async job for status and result.
list_jobsList your recent async jobs.
CursorAdd to ~/.cursor/mcp.json (or the project .cursor/mcp.json) with the same block.

How to install the Extracto MCP server

{
  "mcpServers": {
    "extracto": {
      "command": "npx",
      "args": ["-y", "extracto-mcp"],
      "env": { "EXTRACTO_API_KEY": "exa_live_your_key_here" }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
EXTRACTO_API_KEYCredential the server authenticates with.Yes
EXTRACTO_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Extracto to extract.
  • Use Extracto to extract async.
  • Use Extracto to get job.

Frequently asked questions

It connects Extracto to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (extract, extract_async, get_job, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Extracto directly.