MCP Workspace
MCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.
What is MCP Workspace?
MCP Workspace is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp workspace server: a secure model context protocol server providing file, git, and github tools for ai assistants within a sandboxed project directory.
MCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP Workspace Server: A secure Model Context Protocol server
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-workspaceConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Workspace
MCP Workspace is a secure Model Context Protocol server that provides AI assistants with sandboxed access to a project directory, exposing file system operations, git tools, and GitHub integration. It enforces strict directory boundaries so the AI can only read and write within a designated project folder, preventing accidental access to the rest of your filesystem. Developers use it to let Claude or other MCP clients edit source files, manage project assets, and perform version control operations safely inside a controlled workspace.
Prerequisites
- Python 3.10+ installed on your system
- pip or uv package manager available
- A cloned copy of the mcp-workspace repository from GitHub
- An MCP-compatible client such as Claude Desktop or Claude Code
- Git installed if you intend to use git-related tools
Clone the repository
Clone the mcp-workspace repository from GitHub to get the source code and configuration files.
git clone https://github.com/MarcusJellinghaus/mcp-workspace.git
cd mcp-workspaceCreate and activate a virtual environment
Create an isolated Python environment to avoid dependency conflicts with other projects on your machine.
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activateInstall the package
Install mcp-workspace and its dependencies from the project's pyproject.toml in editable mode.
pip install -e .Test the server manually
Run the server once from the command line to confirm it starts correctly. The --project-dir flag is required and sets the sandboxed directory the AI can access.
mcp-workspace --project-dir /path/to/your/project --log-level INFOConfigure your MCP client
Add mcp-workspace to your Claude Desktop or other MCP client configuration file. Replace the path with your actual project directory.
{
"mcpServers": {
"workspace": {
"command": "mcp-workspace",
"args": ["--project-dir", "/path/to/your/project"]
}
}
}Optionally add reference projects
Use --reference-project to mount additional read-only directories the AI can consult (for example, documentation or shared libraries) without being able to modify them.
mcp-workspace --project-dir /my/project \
--reference-project docs=/my/shared-docs \
--log-level INFOMCP Workspace Examples
Client configuration
Claude Desktop config with a sandboxed project directory and a read-only reference docs folder.
{
"mcpServers": {
"workspace": {
"command": "mcp-workspace",
"args": [
"--project-dir", "/Users/you/projects/my-app",
"--reference-project", "docs=/Users/you/shared-docs",
"--log-level", "INFO"
]
}
}
}Prompts to try
Example prompts that use mcp-workspace file and directory tools inside the sandboxed project.
- "List all files in the project directory and summarize the structure."
- "Read the contents of src/main.py and explain what it does."
- "Create a new file called NOTES.md with a summary of today's changes."
- "Edit config.json to change the port from 8080 to 3000."
- "Move utils/helpers.py to lib/helpers.py."Troubleshooting MCP Workspace
"mcp-workspace: command not found" after installation
Ensure your virtual environment is activated and that the venv's bin directory is on your PATH. Run `which mcp-workspace` inside the venv to confirm the binary exists.
Server refuses to read or write a file outside the project directory
This is by design — the sandbox restricts all operations to --project-dir. If you need access to additional paths, add them as read-only references with --reference-project name=/path.
Claude Desktop does not see the workspace tools after editing the config
Restart Claude Desktop completely after saving claude_desktop_config.json. Also verify the path in --project-dir exists on disk; a missing directory causes the server to fail silently.
Frequently Asked Questions about MCP Workspace
What is MCP Workspace?
MCP Workspace is a Model Context Protocol (MCP) server that mcp workspace server: a secure model context protocol server providing file, git, and github tools for ai assistants within a sandboxed project directory. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Workspace?
Follow the installation instructions on the MCP Workspace GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Workspace?
MCP Workspace works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Workspace free to use?
Yes, MCP Workspace is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MCP Workspace Alternatives — Similar Developer Tools Servers
Looking for alternatives to MCP Workspace? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Workspace in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Workspace?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.