rusiaaman/wcgw
by Various
Shell and coding agent on mcp clients
MCP
rusiaaman/wcgw
Added 1 June 2026
Overview
wcgw is an open-source Python tool that acts as a shell and coding agent for MCP (Model Context Protocol) clients. It exposes shell command execution and code running capabilities through the MCP interface, enabling AI models to interact with the user's system programmatically.
Best for
Best for
Developers using MCP clients who need a lightweight shell and coding agent
Use cases
- Executing shell commands from an MCP client
- Running code snippets in various languages via the agent
- Automating development workflows through MCP-based tools
How to use
Tools exposed
uvx
Tested with
Claude Desktop, VS Code
Example client config
{\n "mcpServers": {\n "wcgw": {\n "command": "uvx",\n "args": ["--python", "3.12", "wcgw@latest"]\n }\n }\n} Notes
wcgw is an open-source Python tool that acts as a shell and coding agent for MCP (Model Context Protocol) clients. It exposes shell command execution and code running capabilities through the MCP interface, enabling AI models to interact with the user’s system programmatically.
660 stars on GitHub. Last updated 2026-04-29. Licensed Apache-2.0.
Use cases
- Executing shell commands from an MCP client
- Running code snippets in various languages via the agent
- Automating development workflows through MCP-based tools
Pros
- Open source with 660 GitHub stars, indicating community interest
- Written in Python, making it accessible for customization
- Integrates directly with MCP clients for seamless agent interaction
Cons
- Requires an MCP client to function, limiting standalone use
- Setup and configuration may be needed for different environments
- Documentation is primarily in a single Readme, potentially sparse
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Open source with 660 GitHub stars, indicating community interest
- Written in Python, making it accessible for customization
- Integrates directly with MCP clients for seamless agent interaction
Cons
- Requires an MCP client to function, limiting standalone use
- Setup and configuration may be needed for different environments
- Documentation is primarily in a single Readme, potentially sparse
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.