Python Testing Tools MCP Server

Created By
jazzberry-ai10 months ago
An advanced Model Context Protocol (MCP) server that provides AI-powered Python testing tools. This project leverages both Google's Gemini AI and BAML (Boundary ML) to intelligently generate comprehensive unit tests and perform sophisticated fuzz testing on Python code.
Overview

Python Testing Tools MCP Server

An advanced Model Context Protocol (MCP) server that provides AI-powered Python testing tools. This project leverages both Google's Gemini AI and BAML (Boundary ML) to intelligently generate comprehensive unit tests and perform sophisticated fuzz testing on Python code.

Overview

This MCP server offers automated testing capabilities through three main tools:

  1. Intelligent Unit Test Generation - Automatically creates comprehensive test suites with proper edge cases, assertions, and error handling
  2. AI-Powered Fuzz Testing - Generates diverse, challenging inputs to test function robustness and discover potential crashes
  3. Advanced Coverage Testing - Generates comprehensive test suites designed to achieve maximum code coverage with intelligent branch, loop, and exception path analysis

The server uses a hybrid AI approach: BAML for structured test generation and Gemini for intelligent input generation, ensuring high-quality, reliable test outputs.

Key Features

  • AI-Powered Unit Test Generation: Uses BAML with Gemini to generate comprehensive unittest suites covering normal cases, edge cases, and error conditions
  • Intelligent Fuzz Testing: Leverages AI to generate diverse, challenging inputs that test function boundaries and error handling
  • Advanced Coverage Testing: AST-based code analysis with AI-generated tests targeting specific coverage scenarios for maximum line and branch coverage
  • Built-in Coverage Measurement: Integrates coverage.py library for real-time coverage reporting and analysis
  • BAML Integration: Structured AI responses using BAML (Boundary ML) for consistent, parseable test generation
  • FastMCP Framework: Built on FastMCP for efficient MCP server implementation
  • Robust Error Handling: Graceful fallbacks and detailed error reporting throughout the testing pipeline
  • Modular Architecture: Clean separation between tools, utilities, and AI clients for easy extension
  • Advanced Code Analysis: Uses Python AST parsing for accurate function extraction, branch detection, and control flow analysis

Server Config

{
  "/path/to/your/project": {
    "mcpServers": {
      "python_testing_tools": {
        "type": "stdio",
        "command": "uv",
        "args": [
          "run",
          "--with",
          "fastmcp",
          "fastmcp",
          "run",
          "/path/to/your/project/python_testing_mcp_server.py"
        ],
        "env": {
          "GEMINI_API_KEY": "your-api-key-here"
        }
      }
    }
  }
}
Project Info
Created At
10 months ago
Updated At
10 months ago
Author Name
jazzberry-ai
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

20 hours ago
Gpt Scrambler

2 days ago