Local Testing Agent

Provides multi-language test discovery, planning, and execution with JSON and Markdown reports for MCP clients.

python

0

GitHub Stars

python

Language

6 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": {
    "marcelkurvers-local-testing-agent": {
      "command": "/path/to/local-testing-agent/.venv/bin/python",
      "args": [
        "/path/to/local-testing-agent/testing_agent.py"
      ]
    }
  }
}

You can run a dedicated Local Testing Agent MCP Server to automatically discover, plan, and execute tests across multiple programming languages. It integrates with MCP clients to enable AI assistants to explore test coverage, generate intelligent plans, and produce comprehensive reports.

How to use

You use this MCP server by running it locally and connecting an MCP client to it. The server exposes tools that scan a repository, execute detected tests across languages, and generate reports and coverage maps. When you start the server, use the complete runtime command shown in the setup instructions to ensure the client can discover and communicate with it properly.

How to install

Prerequisites must be in place before you run the server. You need Python 3.11 or higher and pip.

Step by step commands to set up locally:

# 1) Create a project directory and navigate into it
mkdir local-testing-agent
cd local-testing-agent

# 2) Set up a Python virtual environment
python3 -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# 3) Install runtime dependencies
pip install -r requirements.txt

# 4) Install language-specific test frameworks if you need them
# Python is already included; you can add others as needed
# Example for Python
pip install pytest
# Example for JavaScript/TypeScript (optional, if you plan to test JS/TS projects)
npm install -g jest

# 5) Ensure the MCP server can be started from the local project

Configuration and usage notes

To run the MCP server in a local environment, you can execute the main agent script directly or rely on the MCP tooling that orchestrates scanning, planning, and testing.

# Standalone usage: start the MCP server directly
python testing_agent.py

# Or, if you follow an integrated phase flow, you can trigger the complete pipeline
python -c "from testing_engine.pipeline import full_test_pipeline; full_test_pipeline('.')"

Troubleshooting and notes

If you are using an MCP client like Gravity, you can register the local MCP server by updating the MCP configuration to point at the Python runtime and the testing agent script. Restart the client to apply changes.

Expected output includes an MCP scan snapshot, a test plan, a test report, and a coverage map so you can review results and adjust your tests accordingly.

Tools you can use

The server exposes tools to manage the testing workflow across languages. You can scan repositories, run all detected tests, and execute a full end-to-end pipeline.

Available tools

scan_repository

Scans a project directory and detects source files and test files for all supported languages.

run_all_tests

Runs all detected tests for all languages with test files and generates a combined test report.

full_phase2_pipeline

Runs scan → plan → test → coverage in one end-to-end flow.