How does it work

Created By
pomeriuma year ago
Demo application showcasing how to build and secure MCP servers and clients with Pomerium using contextual access policies.
Overview

What is MCP App Demo?

MCP App Demo is a demonstration application that showcases how to build and secure Model Context Protocol (MCP) servers and clients using Pomerium with contextual access policies.

How to use MCP App Demo?

To use the MCP App Demo, set up your environment by installing Docker and Docker Compose, create a .env file with your OpenAI API key, configure Pomerium settings, and run the application using Docker Compose. You can then access the demo application through your web browser.

Key features of MCP App Demo?

  • Secure access to MCP servers using Pomerium.
  • Integration with OpenAI for AI-powered interactions.
  • Support for OAuth2 authentication flows.
  • Dynamic listing of available MCP servers.

Use cases of MCP App Demo?

  1. Demonstrating secure access to internal databases via external clients.
  2. Enabling AI applications to interact with MCP servers securely.
  3. Showcasing the integration of various OAuth2 providers for authentication.

FAQ from MCP App Demo?

  • What are the prerequisites for using MCP App Demo?

You need a Linux or MacOS host, Docker, Docker Compose, and an OpenAI API key.

  • Is there a way to test the application?

Yes! After setting up, you can navigate to the application URL and interact with the demo database.

  • How does Pomerium enhance security?

Pomerium acts as a secure gateway, managing authentication and authorization for MCP servers, ensuring that sensitive tokens are not exposed to external clients.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
pomerium
Star
2
Language
TypeScript
License
-

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

16 hours ago
Voyei

6 hours ago