A Model Context Protocol (MCP) server for Python debugging using pdb
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":"pdb-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.
# PDB MCP Server [](https://badge.fury.io/py/pdb-mcp) [](https://opensource.org/licenses/MIT) A Model Context Protocol (MCP) server for Python debugging using pdb. This allows you to debug Python scripts through MCP tools. ## Features - **Start Debug Session**: Launch a Python script in debug mode using pdb - **Start Pytest Debug Session**: Run pytest with automatic pdb on test failures - **Execute PDB Commands**: Send commands to control the debugging session - **Auto-detect Python Interpreter**: Automatically uses virtual environment Python - **Modular Architecture**: Clean separation of concerns with session and server modules ## Installation ### Install from PyPI ```bash pip install pdb-mcp ``` ### Install with uv (Recommended) ⚡️ [`uvx`](https://docs.astral.sh/uv/concepts/tools/) will automatically install the package and run the command. ```bash uvx pdb-mcp ``` ### Development Installation ```bash pip install -e . ``` ## Usage ### As MCP Server Run the server: ```bash pdb-mcp ``` The server exposes three tools: #### 1. `start_debug` Start a debugging session for a Python script. **Parameters:** - `script_path` (required): Path to the Python script to debug - `python_path` (required): Path to Python interpreter for the project being debugged - `working_directory` (required): Directory to run the command in (should be the project directory) - `args` (optional): Command-line arguments to pass to the script - `timeout` (optional): Time to wait without new output before returning in seconds (default: 5.0). As long as there's new output, will keep waiting. - `env` (optional): Environment variables to set for the debugging session (e.g., {"DEBUG": "1"}) **Example:** ```json { "script_path": "test_script.py", "python_path": "/path/to/python", "working_directory": "/path/to/project", "env": {"DEBUG": "1"} } ``` #### 2. …
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.