Database · MODEL CONTEXT PROTOCOL

HGraphPunks hedera mcp server

Hedera MCP server

WHAT IT CONNECTS

What HGraphPunks hedera mcp server gives an AI Agent

  • **Agent Registration & Profiles (HCS-11):**
  • **Agent Discovery (HCS-2):**
  • **Secure Communication (HCS-10):**
  • **Large Message Handling (HCS-1 & HCS-3):**
  • **MCP Interface via SSE:**
  • **RESTful API:**
  • **Production-Ready Deployment:**
  • **Node.js** ≥ 18 (LTS recommended)
  • **npm** (comes with Node)
  • **Docker** and **Docker Compose** (for container deployment)
  • A Hedera Testnet (or Mainnet) account with sufficient funds for transactions
  • The REST API is listening on `http://localhost:3000`
  • The MCP SSE server is available at `http://localhost:3001/sse`
  • **POST /api/agents/register**
  • **GET /api/agents/{accountId}**
  • **GET /api/agents?name=Alice&capability=0**
  • **POST /api/connections/request**
  • **POST /api/connections/accept**
  • **GET /api/connections?accountId=0.0.AAAAA**
  • **POST /api/messages/send**
  • **GET /api/messages?connectionTopicId=0.0.CCCCC&limit=10**
  • **Run the Server:**
  • **Configure in Cursor:**
  • **Usage:**
  • **Ensure Environment Variables:**
  • **Build and Run:**
  • **Verify Deployment:**
  • Health Check: `http://localhost:3000/`
  • MCP SSE Endpoint: `http://localhost:3001/sse`
  • **Unit Tests:** Validate logic in individual services (e.g., file chunking in `fileService.test.ts`).
  • **Integration Tests:** Test REST API endpoints using Supertest to ensure proper responses.
  • **End-to-End Tests:** Simulate a full agent communication flow (agent registration, connection, and messaging) on Hedera Testnet.
  • **Logging & Monitoring:**
  • **Caching:**
  • **Scaling:**
  • **Security Considerations:**
  • Secure the `.env` file and never expose private keys.
  • For production, implement proper authentication/authorization for API endpoints.
  • Consider using HTTPS and other secure communication practices.
  • **Standards Compliance Updates:**

SECURITY

An MCP listing is not a security review

An MCP server may receive model context, credentials, local files, or permission to call external systems. Review its code, requested environment variables, network behavior, package provenance, and maintenance status before connecting it to an agent.