Skip to main content
Glama
Sign In

Firecrawl

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Scrape

scrape
Read-onlyIdempotent

Scrape a single URL using Firecrawl's JS-rendering engine and return clean markdown (up to 100,000 chars), page title, and description. Strips navigation/boilerplate by default (only_main_content=true). Supports output formats: markdown, html, rawHtml, links.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "https://en.wikipedia.org/wiki/Web_scraping"
    },
    "name": "scrape"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe URL to scrape, e.g. "https://example.com/article"
_apiKeyNoOptional — your own Firecrawl API key for higher limits; omit to use the shared Pipeworx key.
formatsNoOutput formats to return (default ["markdown"]). Options include "markdown", "html", "rawHtml", "links".
only_main_contentNoStrip navigation, footers, and boilerplate, returning just the main content (default true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "url": "https://example.com/article"
-  },
-  {
-    "formats": [
-      "markdown",
-      "links"
-    ],
-    "only_main_content": true,
-    "url": "https://blog.example.com/post"
-  }
-]New value: +[
+  {
+    "url": "https://en.wikipedia.org/wiki/Web_scraping"
+  },
+  {
+    "formats": [
+      "markdown",
+      "links"
+    ],
+    "only_main_content": true,
+    "url": "https://en.wikipedia.org/wiki/Model_Context_Protocol"
+  }
+]
  2. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "url": "https://example.com/article"
+  },
+  {
+    "formats": [
+      "markdown",
+      "links"
+    ],
+    "only_main_content": true,
+    "url": "https://blog.example.com/post"
+  }
+]
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

The description adds meaningful behavioral context beyond the annotations: JS rendering, default boilerplate stripping, a 100,000-character limit, and the return of title/description. There is no contradiction with the read-only, idempotent, non-destructive annotations.

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

Conciseness5/5

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

The description is front-loaded and compact: three sentences cover what the tool does, what it returns, its main default behavior, and its output options. No wasted words.

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

Completeness5/5

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

For a tool with no output schema, the description does a strong job of describing what the agent can expect: clean markdown, size limits, default main-content filtering, and selectable output formats. The schema overlays the remaining param-level details.

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

Parameters3/5

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

The schema already provides 100% parameter coverage for url, _apiKey, formats, and only_main_content. The description mostly restates schema details like formats and only_main_content rather than adding substantially new parameter-level insight.

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

Purpose5/5

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

The description clearly states the action ('Scrape a single URL'), the engine used (Firecrawl's JS-rendering engine), and the return value (clean markdown, page title, description). It clearly differentiates this tool from sibling research/search tools.

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?

The description gives clear guidance: this is for a single URL and supports multiple output formats. It does not explicitly say when not to use it or name alternative tools, so it falls just short of full usage guidance.

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

All Firecrawl toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources