cleanfetch
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLEANFETCH_UA | No | Override the User-Agent header. | |
| CLEANFETCH_TIMEOUT_MS | No | Request timeout in milliseconds (default 15000). | 15000 |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_cleanA | Fetch a web page and return its main article content as clean Markdown plus core metadata (title, byline). Strips navigation, ads, and scripts so an agent can read the page reliably. |
| extract_linksA | Fetch a page and return all hyperlinks with their anchor text, each classified as internal or external. Useful for crawling and agent navigation. |
| extract_metadataA | Fetch a page and return structured metadata: title, description, canonical URL, robots, Open Graph tags, JSON-LD blocks, and a headings outline. Lets an agent analyze a page's structure without reading the whole body. |
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 3 tools
Each tool targets a distinct aspect of web page analysis: links, metadata, and clean content. There is no functional overlap between extract_links, extract_metadata, and fetch_clean.
Tools follow a verb_noun pattern, but fetch_clean uses 'fetch' while the other two use 'extract'. This is a minor inconsistency but still clear and predictable.
Three tools is a well-scoped set for a clean fetching utility, covering the essential operations without unnecessary complexity.
The tools cover all key aspects of web page extraction: links, metadata, and clean content. No obvious gaps for the stated purpose of agent navigation and analysis.