Tox Testing
Executes tox commands to run Python tests with pytest. Requires the TOX_APP_DIR environment variable to be set.
Tox Testing MCP Server
An MCP server that executes tox commands to run python tests within a project using pytest. This server provides a convenient way to run and manage python tests through the Model Context Protocol (MCP).
Features
Tools
run_tox_tests- Execute tox tests with various modes and options- Supports different execution modes:
all: Run all tests or tests from a specific groupfile: Run tests from a specific filecase: Run a specific test casedirectory: Run all tests in a specified directory
- Test groups supported:
clients: Client-related testsapi: API endpoint testsauth: Authentication testsuploads: Upload functionality testsroutes: Route handler tests
- Supports different execution modes:
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Installation
To use with VSCode, add the server config to your MCP settings file at:
~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
{
"mcpServers": {
"tox-testing": {
"command": "node",
"args": ["/path/to/tox-testing/build/index.js"],
"env": {
"TOX_APP_DIR": "/path/to/your/python/project",
"TOX_TIMEOUT": "600"
}
}
}
}
Configuration Options
env.TOX_TIMEOUT: (Optional) Maximum time in seconds to wait for test execution to complete. If a test run takes longer than this timeout, it will be terminated. Default is 600 seconds (10 minutes)env.TOX_APP_DIR: (Required) Directory containing the tox.ini file. This is where tox commands will be executed from. The path should point to the root of your Python project where tox.ini is located.
The timeout is particularly important for:
- Preventing hung test processes
- Managing long-running integration tests
- Ensuring CI/CD pipelines don't get stuck
Usage
The server provides a single tool run_tox_tests that can be used in different modes:
Tool Arguments
// Run all tests
{
"mode": "all"
}
// Run tests from a specific group
{
"mode": "all",
"group": "api"
}
// Run tests from a specific file
{
"mode": "file",
"testFile": "tests/test_api.py"
}
// Run a specific test case
{
"mode": "case",
"testFile": "tests/test_api.py",
"testCase": "test_endpoint_response"
}
// Run tests from a specific directory
{
"mode": "directory",
"directory": "tests/api/"
}
Using with Cline
When using this MCP with Cline, you can configure Cline's Custom Instructions to handle test execution efficiently. Here's a recommended workflow:
If asked to run tests on the project, use the tox-testing MCP. Follow these steps:
1. Run all tests across the project unless you are given instructions to run a specific test file or test case.
2. Review and rerun each failed test case individually as you troubleshoot and fix the issue from its output.
3. Repeat step 2 until the testcase passes.
4. Once all failed test cases from step 1 are passing rerun all tests again and repeat all steps until all tests pass.
This workflow ensures:
- Comprehensive test coverage by running all tests first
- Focused debugging by isolating failed test cases
- Verification of fixes by retesting individual cases
- Final validation by running all tests again
Example interactions with Cline:
You: Run the tests for this project
Cline: I'll use the tox-testing MCP to run all tests:
{
"mode": "all"
}
You: Fix the failing test in test_api.py
Cline: I'll first run the specific test file:
{
"mode": "file",
"testFile": "tests/test_api.py"
}
Then address each failing test case individually:
{
"mode": "case",
"testFile": "tests/test_api.py",
"testCase": "test_endpoint_response"
}
Contributing
Please see CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.
Related Servers
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Gemini CLI RAG MCP
A RAG-based Q&A server using a vector store built from Gemini CLI documentation.
SeedDream 3.0
Generate images using Bytedance's SeedDream 3.0 model via the FAL AI platform.
Just Prompt
A unified interface for various Large Language Model (LLM) providers, including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.
ExMCP Test Server
An Elixir-based MCP server for testing and experimenting with the Model Context Protocol.
Bruno MCP Server
Execute Bruno collections using the Bruno CLI, with support for environment files and detailed test results.
aidemd-mcp
Structured .aide spec files that give AI agents progressive disclosure into your codebase architecture. 6 MCP tools, 8 slash commands, TUI wizard, multi-IDE support.
GraphQL MCP Server
A strongly-typed MCP server that provides seamless access to any GraphQL API.
Gitlab MCP Server
Model Context Protocol (MCP) server for GitLab — exposes 1006 GitLab REST & GraphQL API operations as MCP tools (28 meta-tools / 43 enterprise), 24 resources, 38 prompts, and 17 completion types for AI assistants. Written in Go, single static binary, stdio and HTTP transport.
LLM API Benchmark MCP Server
Benchmark LLM APIs for throughput and Time To First Token (TTFT) under various concurrency levels.
Terminal MCP Server
Execute commands on local or remote hosts via SSH. Supports session persistence and environment variables.