MCP Ahrefs Server

Ahrefs MCP Server

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "sagaaidev-mcp-ahrefs": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "-m",
        "mcp_ahrefs.server.app"
      ]
    }
  }
}

You run an MCP server for Ahrefs data within the SAAGA ecosystem. This server exposes tools you can call through an MCP client, with SAAGA decorators handling errors, logging, and optional parallel execution. You can operate it locally via STDIO or connect through SSE for web-based clients.

How to use

Connect to the MCP Ahrefs server from your MCP client using either STDIO (local) or SSE (web) transport. The server exposes tool endpoints that your client can invoke with string parameters. SAAGA decorators take care of error handling, logging, and optional parallel execution so you can focus on building your workflow.

To start using it locally via STDIO, run the server with one of the provided commands and let your client communicate through the standard input/output channel. You can choose the direct Python module invocation or the higher-level UV wrapper that manages the process.

How to install

Prerequisites you need before installing: Python 3.12 or higher and UV, the fast Python package manager.

Install from source by cloning the project, setting up the virtual environment with UV, and syncing dependencies.

# Install UV (if not already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh  # On macOS/Linux
# Or visit https://github.com/astral-sh/uv for Windows instructions

git clone <your-repository-url>
cd mcp_ahrefs
uv venv
uv sync

Admin and runtime notes

Run the server in STDIO mode for MCP clients like Claude Desktop or other local clients.

Run the server in SSE mode to support web-based MCP clients.

See the available command-line options to tailor host, port, transport, and log level.

Configuration and runtime commands

STDIO mode commands start the server in a local, file-based communication channel. Choose one of these to begin.

uv run python -m mcp_ahrefs.server.app

uv run python mcp_ahrefs/server/app.py

Software options and UI

You can also access an admin web interface for configuration, monitoring, and log viewing. Start the UI with Streamlit to manage and observe the MCP server.

uv run streamlit run mcp_ahrefs/ui/app.py

Available tools

echo_tool

A tool that echoes back a provided message or processes it as part of a workflow.

calculate_fibonacci

Computes the Fibonacci number for a given input parameter to support mathematical tool chaining.