How do I use Fraim Context MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Fraim Context MCP search for API authentication docs in deep mode" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Fraim Context MCP

Semantic search MCP server for project documentation.

Version: 5.1.0
Status: In Development

Overview

Fraim Context MCP exposes project documentation to LLMs via the Model Context Protocol (MCP). It supports:

Fast mode: Direct cache/search for immediate results
Deep mode: Multi-round synthesis for complex queries
Hybrid search: Vector similarity + full-text search with pgvector
Smart caching: Redis with corpus versioning for cache invalidation

Quick Start

# 1. Setup Doppler doppler login doppler setup # Select: fraim-context → dev # 2. Install dependencies uv sync # 3. Verify environment doppler run -- uv run python scripts/verify_env.py # 4. Run tests doppler run -- uv run pytest tests/stage_0/ -v

Development

This project uses Test-Driven Development (TDD). See DNA/DEVELOPMENT_PLAN.md for stages.

# Run all tests doppler run -- uv run pytest tests/ -v # Run specific stage doppler run -- uv run pytest tests/stage_0/ -v # Lint uv run ruff check src/ tests/ # Type check uv run mypy src/fraim_mcp