Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Extract structured data from a web page

web_extract_run
Read-onlyIdempotent

Extract structured fields from a web page using a CSS selector schema with a base selector and field rules for text, attributes, HTML, or regex.

Instructions

Extract structured fields from a web page using a CSS selector schema. Requires url and schema. schema is required. Example: {"url":"https://example.com/blog","schema":{"name":"posts","baseSelector":"article","fields":[{"name":"title","selector":"h2","type":"text"}]}}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>",
      "schema": "<schema>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "web_extract_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesRequired. Web page URL to fetch.
proxyNoMost expensive proxy tier to use. The page is tried on `datacenter` first and moves up only if it is blocked, stopping at this tier. Default: every tier (`mobile`).
schemaYesCSS selector-based JSON extraction schema: baseSelector plus fields.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
waitForNoWait for a CSS selector before extraction. Must be prefixed with "css:" (e.g. css:main). JavaScript wait conditions are not supported.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
maxCreditsNoMost credits this call may cost (2–25). Default 2, which loads about 3.2 MB on the datacenter proxy or 380 KB on residential or mobile. Raise it for heavy pages; you're charged only for what the page uses.
scanFullPageNoWhen true, scroll the page to load dynamically appended content.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds a concrete schema example that clarifies the extraction contract, but says nothing about return shape, failure modes when selectors match nothing, or how the waiting/credit mechanics interact with extraction — all of which live in the schema rather than the prose. Adds some value, not rich context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The example is front-loaded and useful, but the sentence 'Requires `url` and `schema`. schema is required.' says the same requiredness twice, which is dead weight. It is short overall but not tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description never says what the extracted result looks like or how fields map to the response, which is the most notable gap for an extraction tool. The 9 parameters, including a required nested schema object, are otherwise covered by 100%-coverage schema descriptions, so the omission is bounded rather than fatal.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3, and the description earns above that by showing a fully populated schema example with name, baseSelector, and fields — precisely the nested structure an agent is most likely to get wrong from JSON Schema alone. It does not explain the field `type` or `attribute` semantics, but the nested-object example is genuine added meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: extract structured fields from a web page using a CSS selector schema. An agent can distinguish this from web_markdown_generate or web_ask_run by the phrase 'structured fields ... CSS selector schema'. It does not explicitly name the siblings it competes with, so it stops short of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The worked example implies the intended usage pattern (point at a page, declare the fields you want), which is meaningful guidance for a tool of this shape. However, there is no when-to-use vs when-not, no mention of when to prefer web_ask_run, web_markdown_generate, or web_crawl_run, and no stated prerequisites for the target page. Usage must be inferred from the example.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools