Skip to main content
Glama
raksha39

mcp-agentic-rag

by raksha39
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

MCP Agentic RAG

A production-ready Retrieval-Augmented Generation (RAG) system exposed as an MCP tool. The system searches a local vector knowledge base first; if the query doesn't match well enough, it falls back to live web search. Either way, an LLM generates a grounded, cited answer.

Architecture

User query (via MCP client e.g. Cursor, Claude Desktop)
          │
          ▼
  ┌───────────────────┐
  │   MCP Server      │  server.py
  │  ask_ml_knowledge │
  └────────┬──────────┘
           │
           ▼
  ┌───────────────────┐
  │  Embed query      │  nomic-embed-text-v1.5
  └────────┬──────────┘
           │
           ▼
  ┌───────────────────┐
  │  Search Qdrant    │  cosine similarity
  └────────┬──────────┘
           │
     score >= 0.45?
      /           \
    YES            NO
     │              │
     ▼              ▼
  RAG context   Bright Data
  (local KB)    web search
     │              │
     └──────┬───────┘
            ▼
   ┌─────────────────┐
   │  LLM generates  │  OpenAI / local model
   │  grounded answer│
   └────────┬────────┘
            ▼
   Answer + numbered sources

Related MCP server: MCP RAG Server

Project Structure

mcp-agentic-rag/
├── data/                        # Knowledge base documents
│   ├── machine_learning.txt
│   ├── deep_learning.txt
│   ├── neural_networks.txt
│   ├── cnn.txt
│   ├── rnn.txt
│   ├── transformers.txt
│   ├── optimization.txt
│   └── regularization.txt
├── eval/
│   └── eval_retrieval.py        # Recall@3 evaluation (30 questions)
├── rag_code.py                  # EmbedData, QdrantVDB, Retriever, AnswerGenerator
├── ingest.py                    # One-time ingestion script
├── server.py                    # MCP server entry point
├── docker-compose.yml           # Qdrant vector database
├── requirements.txt
├── .env.example                 # Copy to .env and fill in credentials
└── notebook.ipynb               # Interactive exploration notebook

Setup

1. Prerequisites

2. Install dependencies

pip install -r requirements.txt

3. Configure environment

cp .env.example .env

Edit .env and fill in at minimum:

Variable

Required

Description

OPENAI_API_KEY

Yes

OpenAI API key for answer generation

OPENAI_MODEL

No

Model name (default: gpt-4o-mini)

OPENAI_BASE_URL

No

Custom endpoint for local LLMs (Ollama, LM Studio)

QDRANT_URL

No

Qdrant URL (default: http://localhost:6333)

SCORE_THRESHOLD

No

Similarity cutoff for web fallback (default: 0.45)

BRIGHT_DATA_USERNAME

No

Bright Data SERP credentials (web fallback only)

BRIGHT_DATA_PASSWORD

No

Bright Data SERP credentials (web fallback only)

4. Start Qdrant

docker compose up -d

Qdrant dashboard: http://localhost:6333/dashboard

5. Ingest the knowledge base

python ingest.py

This embeds all documents in data/ and uploads them to Qdrant. Re-run with --reset after updating documents:

python ingest.py --reset

6. Register the MCP server

Add the following to your MCP client configuration (e.g. Cursor mcp.json, Claude Desktop claude_desktop_config.json):

{
  "mcpServers": {
    "mcp-agentic-rag": {
      "command": "python",
      "args": ["/absolute/path/to/server.py"]
    }
  }
}

The server is now available. Your AI assistant will automatically call ask_ml_knowledge_base when relevant.

Using a Local LLM (no OpenAI account needed)

Install Ollama and pull a model:

ollama pull llama3.2

Set in .env:

OPENAI_BASE_URL=http://localhost:11434/v1
OPENAI_API_KEY=ollama
OPENAI_MODEL=llama3.2

Evaluation

Run the built-in Recall@3 evaluation on 30 domain-specific questions (requires Qdrant running with the collection ingested):

python eval/eval_retrieval.py

Save full results to JSON:

python eval/eval_retrieval.py --output eval/results.json

Example output:

============================================================
  Results Summary
============================================================
  Total questions : 30
  Correct (hit)   : 26
  Missed          : 4
  Recall@3        : 26/30 = 86.7%
============================================================

Adding More Documents

  1. Create a .txt file in data/ with this header format:

TITLE: Your Document Title
SOURCE: your_file.txt
URL: https://optional-reference-url.com

---

First chunk of text goes here.

---

Second chunk of text goes here.

  1. Re-ingest:

python ingest.py --reset

License

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP RAG Server

    0xrdan
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to search and retrieve information from your knowledge base using RAG (Retrieval-Augmented Generation) with hybrid search, document indexing, and ChromaDB vector storage.
    15 npm
    MIT

  • Qurio MCP Server

    irahardianto
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI coding assistants to search and retrieve information from a locally ingested knowledge base using hybrid search, grounded in user-curated documentation.
    17
    MIT

  • local-docs-mcp

    nguyenchiencong
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to perform semantic, hybrid, and filtered search on indexed local documentation with RAG capabilities.
    2
    MIT