Database · MODEL CONTEXT PROTOCOL

HGraphPunks hedera mcp server

Hedera MCP server

WHAT IT CONNECTS

HGraphPunks hedera mcp server 为 AI Agent 提供什么

  • **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

MCP 收录不等于安全审核

MCP 服务器可能获得模型上下文、凭据、本地文件或调用外部系统的权限。连接 Agent 前,请检查代码、环境变量、网络行为、软件包来源与维护状态。