mcp-server

coding-tools-mcp: AI coding

Give AI agents coding ability with coding-tools-mcp, a Python tool.
846 stars144 forksPythonGuide quality 9/10Updated 8/18/2026100% free · open source
What it does

Give any AI agent the ability to code using the coding-tools-mcp Python tool

When to use it
  • When you need to integrate coding capabilities into an AI agent
  • For automating repetitive coding tasks using AI
  • To experiment with AI-generated code for prototypes or proofs-of-concept
Ready-to-paste prompt
python main.py --agent=mcp --task=generate_code --language=python --problem_description='Create a simple REST API'
Heads up: Ensure you have Python 3.8 or higher installed, as the tool has specific dependencies that may not be compatible with lower versions
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/coding-tools-mcp && curl -fsSL https://workflowstacks.com/api/skills/coding-tools-mcp/claude-skill -o ~/.claude/skills/coding-tools-mcp/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How coding-tools-mcp: AI coding works
Codeflow
Free to inspect

Coding-tools-mcp: AI coding is a medium Python project (~14k lines across 63 code files, plus 44 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Medium codebase
~14k lines · 63 code files · ~2 h to skim
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Python · Docker
No API keys detected
Python 94%Shell 3%JavaScript 2%TypeScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    coding_tools_mcp/server.py
    Where the program starts running
  4. 4
    pyproject.toml
    Dependencies and the commands it exposes
  5. 5
    coding_tools_mcp/__init__.py
    Inside coding_tools_mcp/ — the main logic begins here
What's in each folder
coding_tools_mcp/Core code — the actual logic17 files
apps/Sub-packages / plugins13 files
integrations/Sub-packages / plugins7 files
packages/Sub-packages / plugins7 files
docs/Documentation29 files
reports/Folder76 files
benchmarks/Evaluations & benchmarks32 files
scripts/Helper scripts9 files
READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
xyTom
Language
Python
Category
mcp-server
Published
5/21/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.