@rethunk/mcp-multi-root-git
Provides comprehensive git tooling via MCP, including status, diffs, commits, branches, stashes, and multi-root inventory, enabling AI agents to manage repositories.
README
@rethunk/mcp-multi-root-git
git tools over MCP: status, multi-root inventory, HEAD parity, presets, logs, structured and raw diff views, commit inspection, fetch, stash, tag, batch commit, push, merge, cherry-pick, worktrees, soft-reset, blame, branch listing, and reflog. Install and MCP client wiring: docs/install.md only — do not duplicate those steps elsewhere.
Repository: github.com/Rethunk-AI/mcp-multi-root-git · npmjs (manual releases): @rethunk/mcp-multi-root-git · GitHub Packages (CI on each tag): @rethunk-ai/mcp-multi-root-git — see docs/install.md and HUMANS.md Publishing.
Documentation
| Doc | Audience |
|---|---|
| docs/install.md | Single source for prerequisites, running the package, and every supported MCP client (plus from-source and troubleshooting) |
| docs/mcp-tools.md | Tool ids, client naming, format / JSON, resource URI, workspace root resolution (canonical reference) |
| schemas/index.json | Published JSON schemas for all MCP tool parameters (JSON Schema draft 2020-12 format) |
| HUMANS.md | Preset file, dev commands, CI, publishing |
| AGENTS.md | Contributors: implementation map (src/server/ + entry src/server.ts), contract bumps, CI |
| CONTRIBUTING.md | Dev setup, hooks, commit conventions, release checks, and how to add tools |
| SECURITY.md | Disclosure policy, threat model, and repository safety guidance |
| specs/README.md | Active / done / parked specification layout used for repo planning |
Tools at a glance: see the table in docs/mcp-tools.md.
JSON Schemas
All MCP tool parameters are published as JSON Schema (draft 2020-12) documents in the schemas/ directory. Tools and validators can use these schemas to validate tool input arguments without reading source code.
Schema files:
schemas/index.json— Index of all 20 tool schemas with file pathsschemas/{tool_name}.json— Individual schema for each tool (e.g.,schemas/batch_commit.json,schemas/git_status.json)
For programmatic use, read schemas/index.json to discover available tools and their schema files.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.