Crawl4AI MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| crawlB | Crawls a website and saves its content as structured markdown to a file |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools. The purpose is clear and unique.
With a single tool, naming is trivially consistent. The verb 'crawl' appropriately describes the action.
A single tool feels thin for a crawling service, which typically offers multiple options (depth, output formats, etc.). However, for a minimal markdown-only crawler, it is borderline reasonable.
The tool covers the basic crawl-and-save workflow but lacks parameters like depth, page limits, or format selection, which are common gaps for such a service.