Skip to main content
Glama
aibozo

AgenticRAG MCP Server

by aibozo
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

AgenticRAG MCP Server

An intelligent codebase processing server that provides agentic RAG (Retrieval-Augmented Generation) capabilities through the Model Context Protocol (MCP).

Features

  • Intelligent Code Indexing: Automatically chunks and embeds codebases for semantic search

  • Agentic Retrieval: Self-critiquing retrieval loop that ensures comprehensive context

  • Multi-Model Architecture: Uses GPT-4o for retrieval and Claude 3 for planning

  • Live Updates: File system watching for automatic re-indexing

  • Cost Control: Built-in telemetry and budget management

Related MCP server: RAG-MCP Server

Quick Installation

1. Clone and Install

# Clone the repository
git clone https://github.com/aibozo/agenticrag-mcp.git
cd agenticrag-mcp

# Run the installation script
./install.sh

The install script will:

  • Check Python version (3.8+ required)

  • Create a virtual environment

  • Install all dependencies

  • Prompt for your API keys

  • Create necessary directories

  • Generate Claude configuration

2. Add to Claude

After installation, add AgenticRAG to Claude:

Windows (Claude Desktop):

  1. Open %APPDATA%\Claude\claude_desktop_config.json

  2. Add the configuration from claude_config_snippet.json

macOS/Linux (Claude Desktop):

  1. Open ~/.config/claude/claude_desktop_config.json

  2. Add the configuration from claude_config_snippet.json

3. Restart Claude

Restart Claude to load the new MCP server.

Manual Installation

If you prefer to install manually:

# Create virtual environment
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Copy and configure environment
cp .env.example .env
# Edit .env and add your OPENAI_API_KEY

# Add to Claude Desktop
claude mcp add agenticrag python3 /path/to/agenticrag-mcp/mcp_launcher.py

Usage

Once installed, you can use these tools in Claude:

Initialize a Repository

Please index the repository at /path/to/my/project as "myproject"

Search Your Code

Search myproject for "how does authentication work?"

Get Repository Statistics

Show me the stats for myproject

Example Conversation

You: Can you index my FastAPI project at ~/projects/api?

Claude: I'll index your FastAPI project for you.
        [Calls init_repo tool]
        ✓ Successfully indexed repository 'api'
        - Total files: 47
        - Total chunks: 312
        - Total tokens: 52,841
        - Duration: 4.32 seconds

You: How does the authentication middleware work?

Claude: Let me search for information about the authentication middleware.
        [Calls search_repo tool]
        Based on my search, the authentication middleware in your FastAPI project:
        
        1. JWT Token Validation (auth/middleware.py, lines 15-45):
           - Validates Bearer tokens on protected routes
           - Extracts user claims from JWT payload
           - Returns 401 for invalid/expired tokens
        
        2. User Context (auth/middleware.py, lines 50-72):
           - Adds user object to request state
           - Enables access via request.state.user
        
        The middleware is registered in main.py on line 23.

Configuration

Required Environment Variables

# .env file
OPENAI_API_KEY=sk-...        # Required for embeddings and GPT-4
ANTHROPIC_API_KEY=sk-ant-... # Optional, for Claude models

Optional Configuration

# Vector Database
CHROMA_PERSIST_DIRECTORY=./chroma_db

# Logging
LOG_LEVEL=INFO
LOG_FILE=./logs/agenticrag.log

# Models
DEFAULT_EMBEDDING_MODEL=text-embedding-3-large
DEFAULT_LLM_MODEL=gpt-4o

Architecture

agenticrag-mcp/
├── src/
│   ├── agents/          # Agentic RAG implementation
│   │   ├── base.py      # Base agent class
│   │   ├── retriever.py # Self-evaluating retriever
│   │   ├── compressor.py # Result compression
│   │   └── workflow.py  # LangGraph orchestration
│   ├── indexing/        # Code indexing pipeline
│   │   ├── chunker.py   # Semantic code chunking
│   │   ├── embedder.py  # OpenAI embeddings
│   │   └── indexer.py   # Repository indexer
│   ├── storage/         # Vector storage
│   │   └── vector_store.py # ChromaDB interface
│   └── mcp_server.py    # MCP server implementation
├── mcp_launcher.py      # MCP entry point
├── install.sh           # Installation script
└── requirements.txt     # Python dependencies

How It Works

  1. Indexing: The system chunks your code respecting language boundaries and creates embeddings

  2. Retrieval: When you search, an AI agent generates optimized queries and retrieves relevant chunks

  3. Self-Evaluation: The agent evaluates if it has enough context and can perform additional searches

  4. Compression: Results are intelligently summarized to provide clear, actionable answers

Troubleshooting

"No module named 'chromadb'"

Activate the virtual environment:

source venv/bin/activate

"OpenAI API key not found"

Make sure your .env file contains:

OPENAI_API_KEY=your-key-here

"MCP server not found in Claude"

  1. Ensure you've added the configuration to Claude's config file

  2. Restart Claude Desktop completely

  3. Check the logs in ./logs/agenticrag.log

Search returns no results

Ensure you've indexed the repository first using the init_repo tool.

Development

Running Tests

source venv/bin/activate
python -m pytest tests/

Local Testing

# Test indexing
python test_indexing.py

# Test agentic RAG
python test_agentic_rag.py

Contributing

Contributions are welcome! Please:

  1. Fork the repository

  2. Create a feature branch (git checkout -b feature/amazing-feature)

  3. Commit your changes (git commit -m 'Add amazing feature')

  4. Push to the branch (git push origin feature/amazing-feature)

  5. Open a Pull Request

License

MIT License - see LICENSE file for details.

Acknowledgments

If you prefer manual installation:

# Create virtual environment
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Copy and configure environment
cp .env.example .env
# Edit .env with your API keys

Usage

Once installed, you can use these tools in Claude:

Index a Repository

Use the init_repo tool to index a codebase:
- path: /path/to/your/project
- repo_name: my-project

Search Code

Use the search_repo tool to find relevant code:
- query: "How does the authentication system work?"
- repo_name: my-project

Get Statistics

Use the get_repo_stats tool to see indexing statistics:
- repo_name: my-project

Example Conversation

User: Index my Python project at /home/user/myproject

Claude: I'll index your Python project for semantic search.
[Uses init_repo tool with path="/home/user/myproject" and repo_name="myproject"]

User: Find all the database connection code

Claude: I'll search for database connection code in your project.
[Uses search_repo tool with query="database connection" and repo_name="myproject"]
[Returns relevant code snippets with file paths and explanations]

Configuration

The server can be configured via environment variables in .env:

# API Keys (required)
OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...

# Optional configurations
CHUNK_SIZE_TOKENS=1280        # Size of code chunks
MAX_FILE_SIZE_MB=2           # Maximum file size to index
DAILY_BUDGET_USD=100         # Cost control limit

Troubleshooting

Module Not Found

  • Ensure virtual environment is activated: source venv/bin/activate

  • Check installation: pip list | grep agenticrag

API Key Errors

  • Verify keys in .env file

  • Ensure no extra spaces or quotes around keys

  • Check key permissions for required models

Claude Can't Find Tools

  • Verify configuration path is absolute, not relative

  • Check Claude logs: Help → Show Logs

  • Ensure MCP server section exists in config

Server Won't Start

  • Check Python version: python3 --version (need 3.8+)

  • Verify Redis is running: redis-cli ping

  • Check port availability: lsof -i:8000

Performance Issues

  • Adjust CHUNK_SIZE_TOKENS for your codebase

  • Increase EMBEDDING_BATCH_SIZE for faster indexing

  • Monitor costs with get_repo_stats tool

Development

Running Tests

# Activate virtual environment
source venv/bin/activate

# Run all tests
pytest

# Run with coverage
pytest --cov=src

Code Formatting

# Format code
black src tests

# Lint code
ruff check src tests

Project Structure

agenticrag-mcp/
├── src/                    # Source code
│   ├── agents/            # AI agents
│   ├── api/              # API endpoints
│   ├── indexing/         # Code indexing
│   └── storage/          # Vector storage
├── tests/                 # Test files
├── install.sh            # Installation script
├── requirements.txt      # Dependencies
└── .env.example         # Environment template

Contributing

  1. Fork the repository

  2. Create a feature branch: git checkout -b feature-name

  3. Make your changes and test

  4. Submit a pull request

License

MIT License - see LICENSE file for details

Support

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aibozo/agenticRAG-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server