MCP Server
import { Aside } from ‘@astrojs/starlight/components’;
The desktop app includes an MCP (Model Context Protocol) server so AI coding assistants can read your logs.
Endpoint
Section titled “Endpoint”POST http://localhost:17655/mcpJSON-RPC 2.0 protocol over HTTP.
Available tools
Section titled “Available tools”| Tool | Args | Description |
|---|---|---|
list_projects | — | List all projects |
list_buckets | projectId | List buckets for a project |
query_logs | projectId, level?, bucket?, search?, limit?, since?, until? | Query logs with filters |
tail_logs | limit?, level? | Get the latest logs globally |
Usage with Claude Code
Section titled “Usage with Claude Code”Point Claude Code (or any MCP-compatible assistant) at the MCP endpoint:
{ "mcpServers": { "gunsole": { "command": "curl", "args": ["-X", "POST", "http://localhost:17655/mcp"] } }}The AI can then query your application’s logs while debugging — “show me the last 10 errors”, “what happened in the auth bucket in the last 5 minutes”, etc.
Protocol
Section titled “Protocol”Standard JSON-RPC 2.0:
// Initialize{"jsonrpc": "2.0", "method": "initialize", "id": 1}
// List tools{"jsonrpc": "2.0", "method": "tools/list", "id": 2}
// Query logs{ "jsonrpc": "2.0", "method": "tools/call", "id": 3, "params": { "name": "query_logs", "arguments": { "projectId": "my-app", "level": "error", "limit": 20 } }}