extract
Web extraction, OCR (Japanese-strong), invoice and company data for AI agents. x402, no API key.
Install extract in your MCP client
extract is a Model Context Protocol server. Add it to your MCP client config once, restart, and the server's tools become available to your AI assistant. The same JSON snippet below works across all four major clients — only the config file path differs.
- Locate your client's MCP config file.
- Cursor:
~/.cursor/mcp.json - Claude Desktop (macOS):
~/Library/Application Support/Claude/claude_desktop_config.json - Claude Desktop (Windows):
%APPDATA%\Claude\claude_desktop_config.json - VS Code:
Settings → Extensions → MCP - Windsurf:
Settings → MCP Servers
- Cursor:
- Add extract to the mcpServers map — paste the snippet below into your config file. If you already have other MCP servers, merge the entry into the existing
mcpServersobject. - Restart your client so it picks up the new server.
- Verify — ask the assistant to list available tools; extract's tools should appear.
{
"mcpServers": {
"extract": {
"command": "npx",
"args": [
"-y",
"@extract/mcp-server"
],
"note": "Replace with the actual package name from the server's documentation."
}
}
}Install extract in Cursor
Open ~/.cursor/mcp.json in your editor, paste the snippet above into mcpServers, save, and restart Cursor. extract will show up in the assistant's tool list on next launch.
Install extract in Claude Desktop (macOS)
Open ~/Library/Application Support/Claude/claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (macOS). extract will show up in the assistant's tool list on next launch.
Install extract in Claude Desktop (Windows)
Open %APPDATA%\Claude\claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (Windows). extract will show up in the assistant's tool list on next launch.
Install extract in VS Code
Open Settings → Extensions → MCP in your editor, paste the snippet above into mcpServers, save, and restart VS Code. extract will show up in the assistant's tool list on next launch.
Transport
extract supports the following MCP transports. Most AI clients use stdio by default for locally-installed servers.
More build.protocol_tooling.mcp MCP servers
Other Model Context Protocol servers in the same space as extract. Each one adds different capabilities to your AI assistant — pick based on the data sources or workflows you need.
mcp-use
MCP framework and CLI built on the official v2 SDK
mcp
GeoWire MCP server — place search, geocoding, directions, isochrones & area analysis over 10 map providers (no API key to start)
mcp-local-rag
Code intelligence for AI coding assistants — AST-level semantic code search with keyword boost. Index your codebase, search by meaning, keep everything local.
Markus Tenghamn
Blog posts, work experience, projects and contact details for Markus Tenghamn, as MCP tools.
Mapmelon
Search curated community colivings and see who else will be staying during your dates.
Mango Inventory
Inventory management for small organizations: search, assign, report, order, set up by chat.
investbrain
Investment discipline MCP server with RAG, behavior detection, journaling, and market data.
MandateShield AI Payment Authority
Checks signed AI purchase authority and independently verifies supported provider outcomes.
Browse the full MCP server directory or use Stork's one-line install to let your agent pick the right server automatically.
