Skip to main content
Glama

Server Details

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

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.5/5.0

Scored across 5 tools

Disambiguation4/5

The two extraction tools (extract vs extract_batch) and keys.create are clearly distinct, and batch vs single is obvious from the names. The main overlap is between explain_extractor and extractors.list, which are both non-fetching introspection tools whose difference (per-page selectors/version/hit count vs. the catalog of active pages and sample schema) is only clarified by reading descriptions carefully.

Naming Consistency2/5

Three different conventions coexist: a bare verb (extract), verb_noun snake_case (explain_extractor, extract_batch), and namespace dot notation (extractors.list, keys.create). The mix makes it hard to predict whether a tool will be named as an action, an action+object, or a resource.method.

Tool Count5/5

Five tools is well-scoped for a narrow page-extraction service: one auth tool, two introspection tools, and single/batch extraction. Each tool has a clear job and none feels redundant or padding.

Completeness4/5

The lifecycle of getting a key, discovering extractors, inspecting one, and extracting single or in batch is fully covered for a read-only extraction service. Minor gaps remain around key management (no list/revoke/rotate) and no way to inspect a specific extractor's full definition beyond a summary.

Available Tools

5 tools
explain_extractorExplain extractorC
Read-only
Inspect

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

Inputs: url, json_schema, extractor_id.

extractExtract fieldsAInspect

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.

Inputs: url (required), json_schema (required), max_age_s, caller_key.

extract_batchExtract batchAInspect

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.

Inputs: items (required), caller_key.

extractors.listList extractorsA
Read-only
Inspect

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

Inputs: no named parameters.

keys.createCreate caller keyAInspect

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.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables users to extract structured data from a given web page URL by describing the desired data and its fields in a natural language prompt. It returns the requested fields as clean, structured output for use directly within MCP-compatible agents and editors.
      227 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables agents to extract structured, prompt-defined data from any web page by supplying a URL and a description of the fields to retrieve. It exposes this capability as a single tool for use in MCP-compatible clients such as Claude, VS Code, Cursor, and Windsurf.
      227 npm
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources