MCP Pulse
Enables sharing MCP servers with clients, storing tool calls in PostgreSQL, and providing usage analytics via an admin dashboard and API.
README
MCP Pulse — shareable MCP + usage analytics
Platform to share an MCP server with clients, store everything in PostgreSQL, and see which users you have and which tools they use most.
What you get
| Piece | Role |
|---|---|
| Postgres | Users, API keys, every tool call |
MCP endpoint (/mcp) |
What you give clients (HTTP + API key) |
| Admin dashboard | Users, top tools, recent activity |
| Admin API | Create users, rotate keys, suspend access |
Quick start
# 1. Start Postgres
npm run db:up
# 2. Install deps
npm install
# 3. Migrate + seed demo clients
npm run db:migrate
npm run db:seed
# 4. Run platform (dashboard + MCP)
npm run dev
Open http://localhost:3847
- Admin token (default):
change-me-admin-token(set in.envasADMIN_TOKEN) - Paste that token in the left sidebar and click Save
Share MCP with a client
- Open Share MCP (or Users → Add user)
- Create a client — you get a one-time API key
mcp_... - Send them a config like:
{
"mcpServers": {
"shared-mcp-platform": {
"url": "http://YOUR_HOST:3847/mcp",
"headers": {
"Authorization": "Bearer mcp_THEIR_KEY"
}
}
}
}
Every tool call is logged to Postgres under that user.
Built-in demo tools
whoami— client profileecho— connectivity checksummarize_text— short bullet summarylookup_record— sample ORD/CUS lookupsearch_docs— tiny docs search
Replace or extend tools in src/mcp/create-server.ts.
Stdio mode (local Cursor)
For a single local key:
set MCP_API_KEY=mcp_...
npm run dev:mcp
Cursor mcp.json example:
{
"mcpServers": {
"shared-mcp-platform": {
"command": "npx",
"args": ["tsx", "src/mcp/stdio.ts"],
"env": {
"DATABASE_URL": "postgresql://mcp:mcp_secret@localhost:5432/mcp_usage",
"MCP_API_KEY": "mcp_..."
}
}
}
}
Environment
Copy .env.example → .env:
| Variable | Purpose |
|---|---|
DATABASE_URL |
Postgres connection string |
PORT |
HTTP port (default 3847) |
ADMIN_TOKEN |
Dashboard / admin API auth |
MCP_PUBLIC_URL |
URL shown in share snippets |
Admin API (examples)
curl -H "X-Admin-Token: change-me-admin-token" http://localhost:3847/api/stats
curl -H "X-Admin-Token: change-me-admin-token" http://localhost:3847/api/users
Project layout
src/
db/ schema, migrate, seed, queries
mcp/ MCP server (HTTP + stdio) + tools
api/ admin REST API
server.ts dashboard + MCP host
public/ admin UI
Production notes
- Change
ADMIN_TOKENand Postgres password before exposing publicly - Put TLS in front (nginx/Caddy) and set
MCP_PUBLIC_URLtohttps://... - API keys are stored hashed (SHA-256); plaintext is only shown at create/rotate time
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.