NestDaddy

TypedPull

ai.peerfoundry/typedpull · v0.1.0

Return only the schema fields you name from one public web page. No raw HTML.

Connect Remote server

Terminal
claude mcp add --transport http typedpull https://typedpull.peerfoundry.ai/mcp
~/.cursor/mcp.json
{
  "mcpServers": {
    "typedpull": {
      "url": "https://typedpull.peerfoundry.ai/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "typedpull": {
      "type": "http",
      "url": "https://typedpull.peerfoundry.ai/mcp"
    }
  }
}
Claude Desktop
Settings > Connectors > Add custom connector
URL: https://typedpull.peerfoundry.ai/mcp

Tools 5 found in our last check

  • extract

    Return fields from one public page. Call extractors.list for hosts, paths, and the sample schema. You can ask for title, heading, or both. If the page has no extractor, the error points to extractors.list. Call keys.create once. Pass caller_key on every later tools/call.

  • extract_batch

    Run up to 20 extract calls. Each item has its own status. Call extractors.list for the sample schema. Call keys.create once. Pass caller_key on every later tools/call.

  • explain_extractor

    Show selectors, version, and hit count. This does not fetch the page.

  • extractors.list

    List active pages, fields, and a sample schema. This does not fetch a page. No caller key is required.

  • keys.create

    Mint a pf_ caller key. The raw key is shown once. Pass this key on every later tools/call. Send it as the caller_key argument.

Details

Endpointhttps://typedpull.peerfoundry.ai/mcp (Streamable HTTP)
First published31 Oct 2026
Last updated31 Oct 2026
Registry nameai.peerfoundry/typedpull

More search and web servers See all

Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.