claude-rag-mcp
MCP server providing RAG context and failure capture for Claude Code, enabling semantic search across project knowledge and storing/analyzing failures.
README
claude-rag-mcp
MCP server providing RAG (Retrieval-Augmented Generation) context and failure capture for Claude Code.
Features
-
Global Context (RAG): Semantic search across project knowledge
- Architecture patterns, lessons learned, anti-patterns
- Memory or ChromaDB persistence
- Auto-inject relevant context
-
Failure Capture: Store and analyze failures
- Test failures, review rejections, quality gate violations
- SQLite persistence
- Retention policies
MCP Tools (11 total)
Context (7 tools)
| Tool | Description |
|---|---|
context_status |
Get status of the global context module |
context_search |
Semantic search for relevant patterns |
context_list |
List context entries with filtering |
context_get |
Get detailed entry information |
context_add |
Add new knowledge entry |
context_delete |
Delete context entries |
context_prune |
Remove old entries |
Learning (4 tools)
| Tool | Description |
|---|---|
learning_status |
Get failure capture status |
learning_list_failures |
List captured failures |
learning_get_failure |
Get failure details |
learning_prune |
Remove old failures |
Installation
From GitHub
npm install github:VXConsulting/claude-rag-mcp
From GitHub Packages
# Configure .npmrc first
echo "@vxconsulting:registry=https://npm.pkg.github.com" >> .npmrc
npm install @vxconsulting/claude-rag-mcp
Usage with Claude Code
Add to your .mcp.json:
{
"mcpServers": {
"claude-rag-mcp": {
"command": "npx",
"args": ["@vxconsulting/claude-rag-mcp", "serve"]
}
}
}
Or if installed from GitHub:
{
"mcpServers": {
"claude-rag-mcp": {
"command": "node",
"args": ["node_modules/@vxconsulting/claude-rag-mcp/dist/cli.js", "serve"]
}
}
}
Configuration
Create .dev-factory.yml in your project root:
version: 1
globalContext:
enabled: true
provider: memory # or chromadb
autoInject:
enabled: true
topK: 5
types: [architecture, lesson, anti-pattern]
learning:
enabled: true
failureDB:
dbPath: .dev-factory/failures.db
retentionDays: 30
Development
npm install
npm run build
npm test
npm run serve # Start MCP server
License
MIT
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.