Configuration — MCP (Model Context Protocol) ​

Buggregator includes a built-in MCP server that lets AI assistants query your debugging data directly. Connect Claude Code, Cursor, or any MCP-compatible client to browse events, inspect errors, analyze profiling data, and read variable dumps — without leaving your editor.

Enabling MCP ​

MCP is disabled by default. Enable it in buggregator.yaml:

mcp:
  enabled: true

mcp:
  enabled: true

Or via environment variable:

MCP_ENABLED=true

MCP_ENABLED=true

Transport Modes ​

Unix Socket (Default) ​

The server listens on a Unix domain socket. This is the recommended mode for local development.

mcp:
  enabled: true
  transport: socket
  socket_path: /tmp/buggregator-mcp.sock

mcp:
  enabled: true
  transport: socket
  socket_path: /tmp/buggregator-mcp.sock

HTTP/SSE ​

For remote access or when Unix sockets are not available, use HTTP transport:

mcp:
  enabled: true
  transport: http
  addr: ":8001"
  auth_token: my-secret-token     # Optional bearer token

mcp:
  enabled: true
  transport: http
  addr: ":8001"
  auth_token: my-secret-token     # Optional bearer token

When MCP_AUTH_TOKEN is set, all requests must include the Authorization: Bearer <token> header.

Integration with AI Assistants ​

Claude Code ​

Add to your .mcp.json or configure via Claude Code settings:

{
  "mcpServers": {
    "buggregator": {
      "command": "./buggregator",
      "args": ["mcp"]
    }
  }
}

{
  "mcpServers": {
    "buggregator": {
      "command": "./buggregator",
      "args": ["mcp"]
    }
  }
}

The buggregator mcp subcommand bridges stdio to the running Buggregator instance via the Unix socket.

Note: Make sure Buggregator is running with MCP enabled before connecting.

If Buggregator runs in Docker, you can use the HTTP transport instead:

{
  "mcpServers": {
    "buggregator": {
      "type": "url",
      "url": "http://localhost:8001/mcp"
    }
  }
}

{
  "mcpServers": {
    "buggregator": {
      "type": "url",
      "url": "http://localhost:8001/mcp"
    }
  }
}

Cursor ​

In Cursor settings, add the MCP server:

• Command: ./buggregator mcp
• Or use the HTTP URL: http://localhost:8001/mcp

Docker Setup ​

When running Buggregator in Docker with MCP enabled:

services:
  buggregator:
    image: ghcr.io/buggregator/server:latest
    ports:
      - 127.0.0.1:8000:8000
      - 127.0.0.1:8001:8001    # MCP HTTP port
    environment:
      MCP_ENABLED: "true"
      MCP_TRANSPORT: http
      MCP_ADDR: ":8001"

services:
  buggregator:
    image: ghcr.io/buggregator/server:latest
    ports:
      - 127.0.0.1:8000:8000
      - 127.0.0.1:8001:8001    # MCP HTTP port
    environment:
      MCP_ENABLED: "true"
      MCP_TRANSPORT: http
      MCP_ADDR: ":8001"

Available Tools ​

MCP clients can use the following tools to query Buggregator data:

Event Management ​

Sentry ​

VarDumper ​

Profiler ​

Example Usage in Claude Code ​

Once connected, you can ask your AI assistant things like:

• "Show me the latest Sentry errors"
• "What's the stack trace for this exception?"
• "Analyze the profiling data and find the slowest functions"
• "What value was dumped in the last VarDumper event?"