Skip to main content
Glama
ysok
by ysok

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.

Demo

Demo

Related MCP server: code-intel-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.

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

  • 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.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    A local-first codebase intelligence tool that enables AI assistants to research codebases using semantic search, multi-hop relationship discovery, and structural parsing. It allows users to extract architectural patterns and institutional knowledge across 30+ programming languages through an MCP-compatible interface.
    2
    538 PyPI
    1,427
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to semantically search and navigate code repositories using natural language, with support for multiple repos, incremental indexing, and no local install needed.
    -