Custom MCP Server with RAG & Tools
Search latest news headlines via Brave Search API
Provides GPT-based summarization and RAG completions
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Custom MCP Server with RAG & Toolswhat's the weather in Paris?"
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.
Custom MCP Server with RAG & Tools
This project implements a Custom MCP (Multi-tool Control Protocol) server using FastMCP, supporting:
Notes Management (Add / Read / Summarize Notes)
Weather Search (via WeatherAPI)
Brave News Search (via Brave API)
Document Ingestion & RAG Queries (via GroundX)
OpenAI GPT Integration for Summarization & RAG
Features
Append, read, and summarize text notes locally
Get real-time weather info
Search current news headlines via Brave API
Ingest PDFs and perform RAG-based semantic search using GroundX
Supports OpenAI GPT (e.g.,
gpt-4o) for completionsLocal MCP Inspector for testing/debugging
Related MCP server: MCP Weather Notes Server
Installation
1. Using uv (Recommended)
uv lock
uv sync2. Using pip
pip install -r requirements.txtEnvironment Variables (.env)
OPENAI_API_KEY=your_openai_api_key
GROUNDX_API_KEY=your_groundx_api_key
WEATHER_API_KEY=your_weatherapi_key
BRAVE_API_KEY=your_brave_api_key
BUCKET_ID=your_groundx_bucket_idRunning the MCP Server
Development Mode (with Inspector UI)
mcp dev main.pyIf you get authentication errors, run with:
DANGEROUSLY_OMIT_AUTH=true mcp dev main.pyDevelopment Mode with claude desktop app:
mcp install main.py
mcp run mainAvailable Tools & Resources
Tool Name | Description |
| Append note to local file |
| Return all stored notes |
| Generate a prompt to summarize notes using GPT |
| Latest news via Brave Search API |
| Real-time weather from WeatherAPI |
| Upload PDF to GroundX knowledge base |
| Perform RAG search with OpenAI GPT completions |
| Retrieve context text for GPT queries |
API Example (via Inspector)
{
"tool": "fetch_weather",
"args": {
"city": "New York"
}
}Example Workflow
uv sync
cp .env.example .env # setup .env file
mcp dev main.py # start MCP development serverTroubleshooting
Error: Connection Error - Missing Proxy Token
➡️ Solution: Use the URL provided or run:
DANGEROUSLY_OMIT_AUTH=true mcp dev main.pyLicense
MIT License © 2025 Your Name / Your Organization
Generated with ❤️ using MCP, GroundX, OpenAI.
This server cannot be deployed
Maintenance
Related MCP Connectors
Create, search, and update notes in an xNotepad AI notebook, with semantic search and AI Q&A.
- KnowtisOAuthapp.knowtis
Create, search and manage Knowtis collaborative notes from AI assistants.
Cross-session, cross-device memory for your agent: remember and recall notes. No key to start.
- aNotepadOAuthcom.anotepad
AI access to your aNotepad online notes: read, search, write, and organize via 22 tools.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables creating, managing, and searching Markdown notes with support for tags, timestamps, and full-text search. Includes AI prompts for analyzing and summarizing notes.61MIT
- AlicenseNot gradedqualityDmaintenanceProvides real-time weather data from Open-Meteo API and enables creating and retrieving notes stored locally in JSON format.MIT
- AlicenseNot gradedqualityDmaintenanceEnables advanced semantic search and document management by integrating the GroundX API with Claude Desktop and GitHub Copilot. It supports local file uploads, website crawling, and Google Drive synchronization for RAG workflows.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables querying, listing, and summarizing personal knowledge base documents using RAG with hybrid search and LLM.MIT