Protocols & Interfaces

MuninnDB starts four listeners on launch. Each serves a different use case and client type.

MBP — Muninn Binary Protocol

MBP is MuninnDB's native binary protocol over TCP. It uses length-prefixed frames with msgpack serialization and supports pipelining — send multiple requests without waiting for responses. Use MBP for production AI agents where latency matters.

// MBP is default when using muninn:// scheme
mem := muninn.NewMemory("api-key", "muninn://localhost:8747")

REST API

The REST API is available at port 8749 and accepts JSON. It's great for quick integration, scripting, and testing. All endpoints follow a consistent resource model.

# Store an engram
curl -X POST http://localhost:8749/v1/engrams \
  -H "Authorization: Bearer mn_live_abc123" \
  -H "Content-Type: application/json" \
  -d '{"concept": "api key rotated", "content": "...", "tags": ["security"]}'

# Activate — cognitive retrieval
curl -X POST http://localhost:8749/v1/activate \
  -H "Authorization: Bearer mn_live_abc123" \
  -H "Content-Type: application/json" \
  -d '{"context": "what security events happened?", "limit": 5}'

Full REST API reference: REST API Reference →

gRPC

gRPC on port 8748 uses Protobuf for serialization. Good for teams who standardize on gRPC, or when building clients in languages other than Go. The proto definitions are in the repo at proto/muninn.proto.

MCP — Model Context Protocol

MCP (Model Context Protocol) is a standard that lets AI agents like Claude and Cursor connect to external tools. MuninnDB ships with 11 MCP tools built in — no separate server needed.

{"mcpServers": {
  "muninndb": {
    "command": "/path/to/muninndb",
    "args": ["mcp"],
    "env": {
      "MUNINN_KEY": "mn_live_abc123",
      "MUNINN_VAULT": "my-agent"
    }
  }
}