Return only the schema fields you name from one public web page. No raw HTML.
Connect Remote server
claude mcp add --transport http typedpull https://typedpull.peerfoundry.ai/mcp
{
"mcpServers": {
"typedpull": {
"url": "https://typedpull.peerfoundry.ai/mcp"
}
}
}
{
"servers": {
"typedpull": {
"type": "http",
"url": "https://typedpull.peerfoundry.ai/mcp"
}
}
}
Settings > Connectors > Add custom connector
URL: https://typedpull.peerfoundry.ai/mcp
Tools 5 found in our last check
extractReturn 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_batchRun 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_extractorShow selectors, version, and hit count. This does not fetch the page.
extractors.listList active pages, fields, and a sample schema. This does not fetch a page. No caller key is required.
keys.createMint 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
| Endpoint | https://typedpull.peerfoundry.ai/mcp (Streamable HTTP) |
| First published | 31 Oct 2026 |
| Last updated | 31 Oct 2026 |
| Registry name | ai.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.
