Skip to main content

mcp_devtasks MCP Server

This project provides basic development tools as an MCP server, designed to be used with Claude Desktop or any Model Context Protocol (MCP) client. It exposes dev tasks (install, build, lint, test, ci) as callable tools.

UVX Installation and Usage

This project supports UVX for fast, isolated Python package execution, following the Model Context Protocol (MCP) server pattern.

Prerequisites

  • Python 3.10+
  • uvx installed (pip install uv or see uv docs)

Install from PyPI

pip install mcp-devtasks

Development Install

git clone https://github.com/blooop/mcp_devtasks.git
cd mcp_devtasks
pip install -e .

Running the MCP Server with UVX

You can run the MCP server using UVX, which is the recommended approach for integration with tools like Claude Desktop:

uvx mcp-devtasks
  • This will launch the MCP server as defined in this package.

Example Claude Desktop Configuration

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "devtasks": {
      "command": "uvx",
      "args": [
        "mcp-devtasks"
      ]
    }
  }
}

CLI Usage

You can also run the server directly:

python -m main

or, if installed as a script:

mcp-devtasks

Available Dev Tasks

The following dev tasks are exposed as MCP tools:

  • install: Install all dependencies required for the project.
  • build: Build the project.
  • lint: Lint the codebase.
  • test: Run all tests.
  • ci: Run the full CI pipeline.

You can call these tools from your MCP client or Claude Desktop interface.

Dev Task Configuration (mcp_devtasks.yaml)

The dev tasks exposed by this MCP server are configured via a YAML file named mcp_devtasks.yaml in the project root. This file maps task names to the shell commands that will be executed when the corresponding MCP tool is called.

Example mcp_devtasks.yaml

# mcp_devtasks.yaml
# YAML file specifying shell commands for each dev task
install: "echo Installing dependencies... && pixi update"
build: "echo Building project... && pixi run build"
lint: "echo Linting code... && pixi run lint"
test: "echo Running tests... && pixi run test"
ci: "echo Running CI checks... && pixi run ci-no-cover"

You can customize this file to add, remove, or change the commands for your development workflow. Each key becomes an MCP tool, and the value is the shell command that will be run.

Metadata

Release files for mcp-devtasks 0.0.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp-devtasks 0.0.4
File Size Uploaded Provenance
mcp_devtasks-0.0.4.tar.gz 6.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for mcp-devtasks 0.0.4
File Interpreter ABI Platform
mcp_devtasks-0.0.4-py2.py3-none-any.whl Python 2, Python 3 none any Details

Total release size: 12.0 kB

Release files / mcp_devtasks-0.0.4.tar.gz

Download URL mcp_devtasks-0.0.4.tar.gz
Size 6.6 kB
Tags Source
SHA-256 checksum
How to use checksums
89c96533abd3d31ed67e1c42dd7fe2df9f2e64ebb46d7a71ebafe2ba80fc86ed
BLAKE2b-256 checksum
How to use checksums
7491d68cd876f3a175d4c02c7d57e7b53f19d6c4135355eb199fe0ba6d72a1e7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.13

Release files / mcp_devtasks-0.0.4-py2.py3-none-any.whl

Download URL mcp_devtasks-0.0.4-py2.py3-none-any.whl
Size 5.4 kB
Tags Python 2 Python 3
SHA-256 checksum
How to use checksums
3eb7544081b6b9be0b285275cf6b1237541d55a0b553a6de3db4caaba6097db6
BLAKE2b-256 checksum
How to use checksums
f6cc2b4fc2f9a1f3d050ac2a65414077bec3a98c3b38a0e5b51955cd678cdf44
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.13

Security for mcp-devtasks 0.0.4

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page