Crawlora MCP

web_crawl

Run an owner-scoped durable web crawl and return its job ID. Provide a seed URL and limits for pages, depth, bytes and job credits.

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": {
      "idempotency_key": "<idempotency_key>",
      "url": "<url>",
      "limits": "<limits>"
    },
    "name": "web_crawl"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	required,Absolute HTTP or HTTPS seed URL without credentials.
`fetch`	No	HTTP fetch options; browser rendering is currently disabled for crawl jobs.
`scope`	No	Optional seed-host and path scope.
`limits`	Yes	required,Bounded job limits.
`sitemap`	No	Sitemap mode: include, only, or skip. Defaults to include.
`idempotency_key`	Yes	required,Idempotency key of 16 to 128 characters; a replay returns the original job.

Output Schema

Name	Required	Description	Default
`data`	Yes	The tool result payload (shape varies per tool; see each tool's docs resource).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 10, 2026

changedInput schema / properties / limits / properties / timeout_seconds / description

Previous value: -"Total wall-clock deadline including queue time and retries."New value: +"Time limit in seconds once work starts, including retries. A job waits at most 30 minutes in the queue."

AddedOct 9, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare openWorldHint=true and destructiveHint=false, so safety is covered. The description adds two useful behavioral facts beyond the schema: the crawl is 'durable' and it returns a 'job ID' (implying an async, pollable job). It does not mention cost implications, credit reservation semantics, or that results must be fetched via a separate tool, so it is only partially enriching.

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?

Two sentences, zero waste: the core action and return value come first, then the required inputs. Nothing is redundant or padded.

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, so return values need not be explained, and the 100%-covered schema handles parameter detail. The remaining gap is workflow context: the async job lifecycle (poll via web_crawl_status, fetch via web_crawl_results) is only hinted at by 'return its job ID', and the scrape-vs-crawl distinction is absent.

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?

Schema coverage is 100% with detailed nested descriptions (depth-zero behavior, credit ranges, byte accounting), so the schema carries the semantics. The description summarizes the parameters ('seed URL and limits for pages, depth, bytes and job credits') but adds no syntax or constraints beyond the schema. Baseline 3 is appropriate.

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 (run a crawl) and resource (web crawl) plus notable qualifiers: 'owner-scoped', 'durable', and 'return its job ID'. This makes the async-job nature clear. However, it does not differentiate from the sibling web_scrape or the web_crawl_status/results/cancel family, so the agent cannot tell from purpose alone when to prefer this over scraping a single page.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance. It never tells the agent how this differs from web_scrape (single page) or that pacing/polling should use web_crawl_status. Usage is only weakly implied by 'seed URL' and 'depth', leaving the agent to infer the selection rules.

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

All Crawlora MCP tools Inspect

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

Need Help?