A MCP service for retrieving backlink information for any domain using Ahrefs' data
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"backlinks-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Backlinks MCP A MCP (Model Control Protocol) service for retrieving backlink information for any domain using Ahrefs' data. ## Overview This service provides an API to retrieve backlink data for websites. It handles the entire process including captcha solving, authentication, and data retrieval from Ahrefs. The results are cached to improve performance and reduce API costs. > This MCP server is only for learning purposes, please do not abuse it, otherwise the consequences will be self-responsible. This project is inspired by `@哥飞社群`. ## Features - 🔍 Retrieve backlink data for any domain - 🔒 Automatic captcha solving with CapSolver - 💾 Signature caching to reduce API calls - 🚀 Fast and efficient data retrieval - 🧹 Simplified output with the most relevant backlink information ## Installation ### Prerequisites - Python 3.8 or higher - A CapSolver account and API key (register [here](https://dashboard.capsolver.com/passport/register?inviteCode=1dTH7WQSfHD0)) - `uv` installed (on macOS, you might need to install with `brew install uv`) ### Manual Setup 1. Clone the repository: ```bash git clone https://github.com/cnych/backlinks-mcp.git cd backlinks-mcp ``` 2. Install FastMCP with uv: ```bash uv pip install fastmcp ``` 3. Set up your CapSolver API key: ```bash export CAPSOLVER_API_KEY="your-capsolver-api-key" ``` ## Usage ### Running the Service You can use FastMCP to run the service in several ways: #### Install in Claude Desktop To install this server in Claude Desktop and interact with it right away: ```bash fastmcp install src/backlinks_mcp/server.py ``` #### Test with the MCP Inspector For development and testing: ```bash fastmcp dev src/backlinks_mcp/server.py ``` #### Install in Cursor IDE On Cursor Settings, switch to MCP tab, click the `+Add new global MCP server` button, then input the following content: ```json { "mcpServers": { "Backlink MCP": { "command": "uvx", "args": ["bac…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.