$ loading_
Debug Python with natural language, tests, breakpoints, and variable inspection.
This is an open-source MIT-licensed Python debugging MCP server with no declared secrets or remote endpoints, and no clear high-risk red flags are evident from the provided material. Its core capability involves local code execution, test running, and variable inspection, which are inherently high-privilege behaviors for this tool class and should be isolated and used with care, especially given its low maturity.
The material explicitly states that no keys or environment variables are required, and no API tokens, account credentials, or external service authentication needs are described, so credential exposure and abuse risk appears low.
No remote endpoints or external service connections are declared. Based on the provided information, there is no factual indication that user data is exfiltrated to third-party network services.
The system flags executes-code, and the description says it can run tests and perform Python debugging via debugpy/DAP, including breakpoints and variable inspection. This implies local code/process execution and strong runtime control capabilities, which are standard high-privilege behaviors for a debugging tool.
To support debugging, test execution, and variable inspection, the tool would typically need access to project source code, test files, and runtime data in process memory. The material does not show permissions beyond the debugging purpose, but it should be assumed to access local project data and debugging session contents.
Positive factors include auditable source code, an MIT license, and a public GitHub repository. However, the source is a third-party registry, community adoption is 0 stars, maintenance status is unknown, and the README is absent, so evidence of maturity and ongoing maintenance is weak; review the source before using it in sensitive environments.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-debugpy" yet — see the docs or source repo.
Connect to the debugpy session and run the failing pytest test_user_login. Set breakpoints and step through login() to inspect arguments, return values, and exception sources, then summarize the root cause and suggested fix.
A report with test results, key breakpoint observations, the failure root cause, and actionable fix suggestions.
Set a breakpoint at the start of the for loop in process_records(), run it with sample input, and compare how record, status, and error_count change on each iteration to find the step causing the incorrect result.
A step-by-step trace of variable changes, highlighting the exact iteration and logic issue causing the error.
I updated parse_config(). Re-run the relevant tests, place breakpoints on key branches to confirm the new logic executes, and inspect variable values for edge-case inputs to verify they match expectations.
The post-fix test results, breakpoint-based validation findings, and notes on any remaining risks.
Let AI control GDB via MCP for breakpoints, stepping, and inspection.
Enable AI to run live GDB debugging sessions on binaries and processes.
Debug code across languages with breakpoints, stepping, and stack trace inspection.
Connect AI to VS Code debugger for breakpoints, stepping, and code inspection.
Control and debug running Node.js processes through a CDP-to-DAP bridge.
Connect Chrome DevTools so AI can debug pages and inspect performance.