MCP server for broken link detection, monitoring, and AI-powered fix suggestions
Project description
LinkRescue MCP Server
MCP server that exposes LinkRescue's broken link scanning, monitoring, and fix suggestion capabilities to AI agents (Claude, Cursor, etc.).
Built with FastMCP 3.x for the Model Context Protocol.
Run Locally
# Install deps
pip install -r requirements.txt
# Run with FastMCP (streamable HTTP for agent access)
fastmcp run main.py --transport streamable-http --port 8000
# Or run directly
python main.py
The server starts on http://localhost:8000/mcp.
Environment Variables
| Variable | Description | Default |
|---|---|---|
LINKRESCUE_API_BASE_URL |
Your LinkRescue API base URL | http://localhost:3000/api |
LINKRESCUE_API_KEY |
API key for authenticated requests | (empty) |
Without a running LinkRescue API backend, the server returns realistic simulated data — useful for testing and demos.
Connect to Claude Desktop
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"linkrescue": {
"url": "http://localhost:8000/mcp"
}
}
}
Connect to Claude Code
claude mcp add linkrescue --transport http http://localhost:8000/mcp
Test with FastMCP CLI
# List tools
fastmcp list-tools main.py
# Call a tool
fastmcp call-tool main.py health_check '{}'
fastmcp call-tool main.py check_broken_links '{"url": "https://example.com"}'
Deploy to Smithery
- Push this repo to GitHub
- Go to smithery.ai
- Click "Add Server" → paste your GitHub repo URL
- Smithery reads
smithery.yamland deploys automatically
One-liner after pushing to GitHub:
npx @anthropic-ai/claude-code mcp add linkrescue --smithery freedomengineers/linkrescue-mcp
Deploy to Railway / Fly.io
Use the included Dockerfile:
# Railway
railway up
# Fly.io
fly launch
fly deploy
Set env vars in the platform dashboard.
Tools
| Tool | Description |
|---|---|
check_broken_links |
Scan a URL/sitemap for broken links with SEO impact estimates |
monitor_links |
Set up scheduled broken link monitoring |
get_fix_suggestions |
Get prioritized remediation steps from a scan report |
health_check |
Verify server and API connectivity |
Architecture
Agent (Claude/Cursor)
↓ MCP protocol
LinkRescue MCP Server (this repo)
↓ HTTP API calls
LinkRescue API Backend (your existing app)
The MCP server is a thin translation layer. It converts MCP tool calls into LinkRescue API requests and returns structured results agents can act on. If the backend is unreachable, it falls back to simulated data for demo purposes.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file linkrescue_mcp-0.1.0.tar.gz.
File metadata
- Download URL: linkrescue_mcp-0.1.0.tar.gz
- Upload date:
- Size: 8.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0d7d606219fa94f843efa09d02f34886a82d6f5304cda236ab1e9894ff600ed4
|
|
| MD5 |
0f747c7509dfd1ed3e406d0d5fa97ac2
|
|
| BLAKE2b-256 |
60a54d6d5a19dac82baf7878417bac1557ea50a65e88c91210c701caae2efc7e
|
File details
Details for the file linkrescue_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: linkrescue_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 7.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1955d0849bb44c621d3ec32b8e61d5ad22161769819314a8cb9fddc44ccfd9e1
|
|
| MD5 |
1c2f61af9ebac46af80afb3a6e8d2239
|
|
| BLAKE2b-256 |
1b474875e125864e1176a01d28264d8a7bb8093b2263e406410bf11ad117c301
|