url-text-fetcher
README.md
# url-text-fetcher
## URL Text Fetcher Tools
This MCP server provides two utilities for web content analysis.
## How to install
```bash
pip install -e .
```
## How to use with LM Studio
`mcp.json` file:
```json
{
"mcpServers": {
"url-text-fetcher": {
"command": "python",
"args": [
"-m",
"url_text_fetcher.mcp_server"
]
}
}
}
```
## Tools Description
### 1. `fetch_url_text(url: str) → str`
**Description:**
Extracts all visible text content from a webpage, stripping HTML tags and normalizing whitespace.
**Output Format:**
Cleaned plain text with:
- All HTML removed
- Line breaks normalized (`\n`)
- Leading/trailing whitespace stripped
---
### 2. `fetch_page_links(url: str) → List[str]`
**Description:**
Finds all absolute and relative links (from `<a href>` tags) on a webpage.
**Output Format:**
List of URLs including:
- Absolute paths (`/about`)
- Relative paths (`../contact`)
- Full domain URLs (`https://example.com/page`)
TDQS
A3.6/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have clearly distinct purposes: one fetches the text content of a URL, the other extracts links from a page. There is no overlap or ambiguity between them.
Naming Consistency5/5
Both tool names follow the verb_noun pattern consistently: fetch_url_text and fetch_page_links. The naming is clear, predictable, and uniform.
Tool Count3/5
With only two tools, the set feels thin. While the scope is narrow and both tools are useful, this falls at the borderline where 1-2 tools are considered minimal.
Completeness5/5
For a URL text fetcher, the two tools cover the primary needs: retrieving the text content and discovering links on a page. The surface is complete for this simple, read-only domain, with no obvious gaps.
Maintenance
ActivityInactive
ResponsivenessNo issues