Skip to main content
Glama
Sign In
diffbot-mcp

diffbot-mcp

Official
by diffbot
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Extract Page

extract
Read-onlyIdempotent

Fetches a live web page and returns its main content as Markdown or token-efficient typed JSON, rendering JavaScript for public sites.

Instructions

Fetches a live web page and returns its main content as markdown or a token efficient typed JSON record (article, product, discussion, job, event, list). Renders Javascript, so it works on more sites than a plain fetch. Prefer over a generic fetch tool for any public page. API docs: https://www.diffbot.com/docs/extract/

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>"
    },
    "name": "extract"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPage URL; https:// added if missing
formatNo`markdown` for readable text; `json` for typed fields such as title, author, date, price, imagesmarkdown
page_typeNoOverride auto-detection; rarely needed

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the bar is lower; the description still earns credit by disclosing that the tool renders JavaScript and therefore succeeds on sites a plain fetch would miss, plus the dual markdown/typed-JSON output contract. It omits operational caveats like rate limits, authentication requirements, or failure behavior on non-HTML content.

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

Conciseness4/5

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

The capability and output format are front-loaded in the first sentence, with JavaScript rendering and the fetch-comparison following as supporting detail, and the docs URL is a compact pointer rather than prose. Mild redundancy from mentioning "fetch" twice in consecutive sentences keeps it just under top marks.

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

Completeness4/5

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

An output schema exists and all three parameters are fully documented, so the description only needs to carry capability and behavioral context — which it largely does via JS rendering and output formats. For a network-fetching tool, the absence of any note on rate limits, auth, or latency/robots constraints is the remaining gap.

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?

With 100% schema coverage the baseline is 3, and the description adds meaning on top by framing json as "token efficient" and enumerating the record types (article, product, discussion, job, event, list) that the page_type enum controls. It does not explain when overriding auto-detection is warranted, despite the schema calling it "rarely needed".

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?

"Fetches a live web page and returns its main content as markdown or a token efficient typed JSON record" gives a concrete verb, resource, and output shape, and the parenthetical content-type list pins down what the tool produces. It distinguishes itself from a generic fetch but never names or contrasts with actual siblings such as crawl or search_web, so the boundary with those tools stays implicit.

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

Usage Guidelines4/5

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

"Prefer over a generic fetch tool for any public page" is an explicit positive recommendation with a scope qualifier (public pages). It stops short of when-not-to-use conditions — nothing about authenticated/private pages, multi-page fetching (crawl territory), or query-style retrieval (search_web territory) — leaving some inference to the agent.

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