Tribal - Knowledge Service

What is Tribal - Knowledge Service?

Tribal is an MCP (Model Context Protocol) server implementation for error knowledge tracking and retrieval. It provides both REST API and native MCP interfaces for integration with tools like Claude Code and Cline, using ChromaDB for vector similarity search.

How to use Tribal - Knowledge Service?

Install the package with uv pip install . from the project root, then add to Claude using claude mcp add tribal --launch "tribal". Alternatively, deploy via Docker Compose. The server exposes MCP tools such as add_error, get_error, search_errors, and find_similar for managing error records.

Key features of Tribal - Knowledge Service

• Store and retrieve error records with full context.
• Vector similarity search using ChromaDB.
• REST API (FastAPI) and native MCP interfaces.
• JWT authentication with API keys.
• Local storage (ChromaDB) and AWS integration (S3, DynamoDB placeholders).
• Docker-compose deployment and CLI client integration.

Use cases of Tribal - Knowledge Service

• Claude automatically stores programming errors and solutions during a session.
• Search for similar errors when encountering a new problem.
• Build a knowledge base specific to your coding patterns across sessions.
• Integrate with Claude Code or Cline to remember and learn from past errors.

FAQ from Tribal - Knowledge Service

What is Tribal - Knowledge Service?

It is an MCP server that helps Claude remember and learn from programming errors by storing error records with solutions and performing semantic similarity searches.

How do I install Tribal - Knowledge Service?

Install using uv pip install . from the project directory, or use uv tool install . for a global tool. Python 3.12+ and uv are required.

Does Tribal - Knowledge Service require authentication?

Yes, it supports JWT authentication. By default, authentication is disabled (REQUIRE_AUTH=false), but you can enable it by setting environment variables like API_KEY and SECRET_KEY.

What storage backends does Tribal - Knowledge Service support?

The primary storage is local ChromaDB (persistent by default). It also includes placeholder implementations for AWS S3 and DynamoDB for cloud deployment.

Can I run Tribal - Knowledge Service in Docker?

Yes, a docker-compose.yml file is provided. Build and start containers with docker-compose up -d --build, and configure Claude for Desktop to connect to http://localhost:5000.