crawl4tools
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetchA | Fetch one or more web pages and return their content directly: Markdown (default), HTML, or a PNG screenshot. PDFs are transcribed to Markdown and images are returned as images. When several URLs are given, each result starts with a '' header. Failed URLs are reported as 'error: ...' lines; the call fails only if every URL fails. Use |
| downloadA | Fetch one or more URLs and save each result as a file in a directory on the server, returning the saved paths. Supports Markdown (default), HTML, PDF, PNG screenshot, MHTML, and the raw source. PDFs are transcribed to Markdown unless format is 'raw'; non-web content (images, archives, ...) is saved as served. Existing files are overwritten. The call fails only if no file was saved. |
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 2 tools
The two tools, `fetch` and `download`, have clearly distinct purposes: `fetch` returns content directly for immediate consumption, while `download` saves content to files. There is no ambiguity in their intended use cases, even though they share underlying capabilities.
Both tools use consistent short, verb-based names (`fetch` and `download`) that directly reflect their actions. They follow the same naming style (single-word imperative verbs), making them predictable and easy to remember.
With only two tools, the server feels very thin for a general-purpose web fetching service. While each tool is useful, the number is at the lower boundary, and many common operations (e.g., batch processing, URL validation, or content extraction options) are not represented as separate tools. This may be acceptable for a minimal server, but it limits agent flexibility.
The two tools cover basic fetching and downloading, but there are notable gaps: no way to list or manage previously downloaded files, no support for custom headers or POST requests, and no filtering or transformation of content beyond format selection. The surface is functional but misses common needs for a web-fetching domain.