Yuvansh MCP Server
Provides read-only Chatty Pi tools via a streamable HTTP MCP endpoint, enabling access to user profile, posts, notifications, and YuvaBucks balance.
README
Yuvansh MCP Server
Reusable MCP server for Yuvansh projects, starting with Chatty Pi.
Features
- Streamable HTTP MCP endpoint at
/mcp - Health endpoint at
/health - Read-only Chatty Pi tools
- Pagination for list-style tools
- Development mock authentication
- Database/provider-independent Chatty Pi service layer
- Production fail-closed authentication until a trusted OAuth/JWT verifier is added
- No secrets committed to the repository
Local setup
Requirements: Node.js 20+ and npm.
npm install
cp .env.example .env
npm run build
npm start
Development mode:
npm run dev
With ENABLE_MOCK_AUTH=true and NODE_ENV=development, the server authenticates the configured MOCK_USER_ID and uses mock Chatty Pi data. This is for local testing only.
Environment variables
PORT— HTTP port, default3000MCP_PATH— MCP endpoint path, default/mcpNODE_ENV—developmentorproductionCHATTY_PI_API_BASE_URL— Chatty Pi API base URLCHATTY_PI_API_KEY— server-side Chatty Pi API credentialMCP_AUTH_TOKEN— reserved for future trusted authentication integrationMOCK_USER_ID— development-only mock user IDENABLE_MOCK_AUTH— enables development mock mode
Never commit .env or real credentials.
Endpoints
GET /health— service healthPOST /mcp— Streamable HTTP MCP endpoint
MCP tools
get_my_profile— authenticated user's profileget_my_posts— authenticated user's posts, paginatedget_my_notifications— authenticated user's notifications, paginatedget_my_yuvabucks— authenticated user's YuvaBucks balance and transactions
All current tools are read-only. No account deletion, transfers, password changes, or other destructive operations are exposed.
Security
Production requests currently fail closed until a trusted authentication layer is implemented. The server intentionally does not accept a user ID from an MCP client as proof of identity.
Before production deployment, connect the server to an OAuth 2.1/JWT verification layer and derive the Chatty Pi user identity from the verified credential. Do not replace this with a client-supplied header.
Chatty Pi integration
The Chatty Pi API paths /me, /posts, /notifications, and /yuvabucks are placeholders for the eventual Chatty Pi API contract. Keep database-specific logic inside the service layer so the MCP interface does not depend on Zite, Firebase, Google Sheets, or another particular backend.
Production domain
Intended endpoint:
https://mcp.yuvansh.info/mcp
DNS and hosting must be configured separately. Expose the service over HTTPS and configure credentials through the hosting provider's secret manager.
Deployment
Deploy as a normal Node.js HTTP application on a Node-compatible host. Configure environment variables, expose HTTPS, and point mcp.yuvansh.info to the deployed service.
Adding another project
Keep project-specific API calls inside a service module and register new MCP tools in their own module. Do not put database-specific logic directly inside the MCP transport layer.
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.