ai.peerfoundry/typedpull

up checked 2026-11-11T02:37:45.756Z

Unclaimed · Unverified

Publisher-provided title

TypedPull

Publisher-provided description

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

Summary by lookupd

Extracts only named schema fields from a single public web page, single or batched, without returning raw HTML.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http typedpull https://typedpull.peerfoundry.ai/mcp

Codex, remote (streamable-http)

codex mcp add typedpull --url https://typedpull.peerfoundry.ai/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "typedpull": {
      "url": "https://typedpull.peerfoundry.ai/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

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 ex
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 tool
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.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/ai.peerfoundry/typedpull.svg)](https://lookupd.com/servers/ai.peerfoundry/typedpull)