Demo MCP Server
Headless MCP server that exposes MongoDB Atlas and Excel CRUD operations as AI agents over REST and MCP Streamable HTTP, with API-key authentication, plain-English command handling, and optional stdio mode for Cursor.
README
Demo MCP Server (headless)
MCP-only project — no React UI. Connect any React (or other) app over HTTP.
Agents
| Folder | Id | Role |
|---|---|---|
src/agents/mongo/ |
agent-1-mongo |
MongoDB Atlas CRUD |
src/agents/excel/ |
agent-2-excel |
Local Excel .xlsx CRUD |
Any React app
│ POST /api/login { apiKey }
│ Authorization: Bearer <token>
├─► POST /api/agent (plain English)
├─► /api/* (REST Mongo helpers)
└─► /mcp (MCP Streamable HTTP for agent hosts)
│
▼
demo-mcp-server
├── agents/mongo
└── agents/excel
Run
npm install
npm run api # http://127.0.0.1:3000
npm run mcp # stdio for Cursor
Login (from any React app)
Set CLIENT_API_KEY in .env. Then:
const login = await fetch('http://127.0.0.1:3000/api/login', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ apiKey: import.meta.env.VITE_MCP_API_KEY }),
}).then((r) => r.json());
const token = login.token;
const result = await fetch('http://127.0.0.1:3000/api/agent', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${token}`,
},
body: JSON.stringify({ prompt: 'show rows in people' }),
}).then((r) => r.json());
Keep secrets out of the browser bundle when possible (proxy through your React app’s backend). For local demos only, a Vite env var is fine.
CORS
CORS_ORIGIN=* allows any React origin. Or set a comma-separated list:
CORS_ORIGIN=http://localhost:5173,http://localhost:3001
Layout
src/
agents/
mongo/ # Agent 1
excel/ # Agent 2
catalog.ts # Public agent list
orchestrator/ # Plain-English → tool calls (LLM or rules)
mcp/ # MCP factory + stdio
http/ # REST + /mcp + login auth
shared/db/ # Mongo connection helpers
data/workbook.xlsx
Cursor (stdio)
.cursor/mcp.json still points at src/mcp/stdio.ts.
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.
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.
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.
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.
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.
E2B
Using MCP to run code via e2b.