SSOT-MCP
A free, open-source system that indexes multiple Git repositories (e.g., GitHub, GitLab) and enables semantic and lexical search through MCP-capable tools like Cursor.
README
SSOT-MCP (Single Source of Truth — MCP)
SSOT-MCP is a free, open-source system for teams who want one place to index many Git repositories and query them from MCP-capable tools (for example Cursor).
Ingest GitHub or GitLab organizations or individual repositories, run a Prefect pipeline per repo (clone → chunk → embed → index → cross-deps), then search through Chroma (semantic) and Zoekt (lexical) via a dashboard, REST/WebSocket API, or MCP.
Requirements
| Category | What you need |
|---|---|
| Runtime | Podman and podman-compose |
| Imports | GitHub or GitLab token, plus a Hugging Face token for the embedding model |
| GPU (embedding) | NVIDIA GPU strongly recommended for production embed throughput; see docs/README.md |
Quick start
git clone https://github.com/ysok/ssot-mcp.git
cd ssot-mcp
cp .env.example .env
# Edit .env: GITHUB_TOKEN or GITLAB_TOKEN, HF_TOKEN, postgres UIDs, GPU settings
podman-compose up --build
Compose creates data/app and data/postgres on the host. Finish Settings (tokens) before Import or Scan.
| Service | URL |
|---|---|
| Dashboard | http://localhost:8080 |
| API docs | http://localhost:8000/docs |
| Prefect UI | http://localhost:4200 |
Documentation
| Document | Contents |
|---|---|
| docs/README.md | Configuration, data layout, MCP, auth, troubleshooting, local dev |
| docs/ARCHITECTURE.md | Stack, features, deployment topology, Mermaid diagrams |
| docs/PRESENTATION.md | Marp slide deck (overview for teams) |
| .env.example | Environment variables |
| CONTRIBUTING.md | Development and PR expectations |
| CHANGELOG.md | Release notes |
Legal
- License: MIT
- Third-party components: NOTICE (Zoekt, Chroma, Prefect, PyTorch/CUDA, container bases, embedding model)
- Indexed repositories: You must have rights to clone and index any code you register; SSOT-MCP does not grant those rights.
- Trademarks: Names such as Cursor, GitHub, GitLab, and Hugging Face are trademarks of their respective owners; this project is not affiliated with them unless stated otherwise.
Contributing
See CONTRIBUTING.md.
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.