ShadowGit
The ShadowGit MCP Server gives your AI assistant secure, read-only access to your local Git repositories.
It’s built to work with ShadowGit, an application that automatically saves every code change as a commit.
Features
- 🔐 Secure Access: Provides read-only access to Git repositories, blocking any commands that could write or alter files.
- 🔎 Repository Discovery: Automatically lists all projects tracked by the ShadowGit application.
- 🤖 AI Integration: Connects with any AI assistant that supports the Model Context Protocol (MCP), such as Claude Code and Claude Desktop.
- 📜 Detailed History: Lets the AI tap into ShadowGit’s fine-grained, save-by-save history, not just your manual commits.
- ⚡ Direct Git Commands: Allows the AI to execute standard, read-only Git commands like
log,diff, andblamedirectly on your projects.
Use Cases
- Pinpoint Recent Bugs: You’ve been coding for an hour and suddenly something breaks. Instead of manually retracing your steps, you can ask your AI assistant, “Show me all changes in the
my-apprepo from the last hour.” The AI can usegit logvia the MCP server to give you an immediate answer. - Understand Code Evolution: When you encounter a complex function and need to know why it was written a certain way, you can have the AI investigate its history. A request like, “Trace the history of the
calculateTaxfunction insrc/billing.ts” lets the AI usegit log -Lto show you every change made to that specific block of code over time. - Cross-Project Audits: If you work across multiple microservices, you can get a quick status update on all of them. You could ask the AI, “What was the latest activity in each of my tracked repositories yesterday?” The server would list all repos and then run a
git logcommand on each one to summarize the recent changes.
How To Use It
1. Make sure you have Node.js (version 18 or higher) and the ShadowGit desktop app installed and running.
2. Install the MCP server globally from npm with this command:
npm install -g shadowgit-mcp-server3. For Claude Code:
Add the server to Claude Code by running:
claude mcp add shadowgit -- shadowgit-mcp-serverYou’ll need to restart Claude Code for it to recognize the new server.
4. For Claude Desktop:
You have to manually edit the configuration file.
- macOS/Linux:
~/.config/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the shadowgit server to the mcpServers object:
{
"mcpServers": {
"shadowgit": {
"command": "shadowgit-mcp-server"
}
}
}5. Available Commands
list_repos(): This command returns a list of all repositories that your ShadowGit app is tracking.git({repo, command}): This executes a read-only Git command on a specified repository.repo: The name of the repository fromlist_repos().command: The Git command string, like"log --oneline -5"or"diff HEAD~3".
FAQs
Q: Is it safe to give an AI access to my local Git repositories?
A: Yes, the server is designed with security in mind. It only permits read-only Git commands, so the AI cannot perform actions like commit, push, or merge. It also validates that it’s accessing a real ShadowGit repository and filters out potentially dangerous arguments.
Q: What’s the main benefit of this over just using standard Git history?
A: ShadowGit captures every single save you make, creating a much more detailed history than your manual commits. This allows an AI to see the small, incremental steps you took, which is incredibly useful for debugging a problem that occurred between commits.
Q: The server isn’t finding my repositories. What should I do?
A: First, make sure the ShadowGit desktop application is running and you have added projects to it. The server relies on the ~/.shadowgit/repos.json file that the app creates. You can also use the list_repos() command from your AI assistant to see exactly which repository names are available.
Q: Can I use this with other AI assistants besides Claude?
A: Yes, it should work with any AI client that supports the Model Context Protocol (MCP). The setup process will vary depending on the specific tool you use.
Latest MCP Servers
CVE
WebMCP
webmcp is an MCP server that connects MCP clients to web search, page fetching, and local LLM-based extraction. It’s ideal…
Google Meta Ads GA4
Featured MCP Servers
Notion
Claude Peers
Excalidraw
FAQs
Q: What exactly is the Model Context Protocol (MCP)?
A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.
Q: How is MCP different from OpenAI's function calling or plugins?
A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.
Q: Can I use MCP with frameworks like LangChain?
A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.
Q: Why was MCP created? What problem does it solve?
A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.
Q: Is MCP secure? What are the main risks?
A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.
Q: Who is behind MCP?
A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.



