MCP Integration

The Model Context Protocol (MCP) lets AI coding tools access your Corbulo data — health scores, analysis issues, architecture reviews, PR analyses — so they have full context about your codebase quality when helping you write code.

Supported Tools

Tool	Support
Claude Code	Full
Cursor	Full
Windsurf	Full
Claude Desktop	Full

Any MCP-compatible tool can connect to the Corbulo MCP server.

Setup

1. Create an API Key

Go to Settings > API Keys in your Corbulo project and create a new key. Give it a descriptive name like “MCP Server”. Copy the key immediately — it will not be shown again. See API Keys for details on key management.

2. Configure Your Tool

The Corbulo MCP server communicates over stdio and requires two environment variables:

CORBULO_API_KEY — Your API key from step 1
CORBULO_BASE_URL — Your Corbulo instance URL (defaults to https://api.corbulo.dev)

Claude Code
Cursor
Windsurf
Claude Desktop

Add to your MCP configuration (.mcp.json in your project root or ~/.claude/mcp.json globally):

{
  "mcpServers": {
    "corbulo": {
      "command": "corbulo-mcp",
      "env": {
        "CORBULO_API_KEY": "your-api-key",
        "CORBULO_BASE_URL": "https://api.corbulo.dev"
      }
    }
  }
}

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "corbulo": {
      "command": "corbulo-mcp",
      "env": {
        "CORBULO_API_KEY": "your-api-key",
        "CORBULO_BASE_URL": "https://api.corbulo.dev"
      }
    }
  }
}

Add to your Windsurf MCP configuration:

{
  "mcpServers": {
    "corbulo": {
      "command": "corbulo-mcp",
      "env": {
        "CORBULO_API_KEY": "your-api-key",
        "CORBULO_BASE_URL": "https://api.corbulo.dev"
      }
    }
  }
}

Add to your Claude Desktop configuration file (claude_desktop_config.json):

{
  "mcpServers": {
    "corbulo": {
      "command": "corbulo-mcp",
      "env": {
        "CORBULO_API_KEY": "your-api-key",
        "CORBULO_BASE_URL": "https://api.corbulo.dev"
      }
    }
  }
}

The corbulo-mcp binary is available from your Corbulo dashboard under Settings > Downloads, or as part of the self-hosted deployment package.

Available Tools

The Corbulo MCP server exposes 17 tools organized by domain.

Project

Tool	Description
`list_projects`	List all projects accessible with the current API key
`get_project`	Get details for a specific project

Code Health

Tool	Description
`get_health_dashboard`	Overall health score with category breakdown and active drift alerts
`get_health_categories`	All 8 health categories with weights, scores, and baseline thresholds
`get_health_assessment`	Details for a specific assessment
`list_health_assessments`	Assessment history over time
`list_drift_alerts`	Quality regressions detected between assessments

Analysis

Tool	Description
`list_analysis_issues`	All detected issues, with optional filters by severity and category
`get_issue_stats`	Issue counts grouped by category and severity
`list_dismiss_rules`	Active dismiss rules that suppress specific findings

Architecture

Tool	Description
`get_architecture_overview`	Summary of the latest architecture review, conventions, and ADRs
`get_architecture_review`	Latest architecture review with scores across 4 dimensions
`list_conventions`	Detected coding conventions with conformance rates
`list_adrs`	Architecture decision records with lifecycle status

Pull Requests

Tool	Description
`get_pr_analysis`	Analysis results for a specific PR, including merge readiness and issues
`list_pr_analyses`	PR analysis history
`get_pr_stats`	Aggregate PR analysis statistics

Example Usage

With the MCP server connected, your AI coding assistant can answer questions about your codebase using real data from Corbulo. You: “What is the current state of our code health? Are there any critical issues I should focus on?” Your AI assistant will call get_health_dashboard to retrieve the overall score and category breakdown, then list_analysis_issues filtered by critical severity to find the most important issues. The response includes specific file locations, issue descriptions, and which health categories are most affected. You: “I am about to refactor the authentication module. What conventions does the codebase follow for error handling?” Your AI assistant will call list_conventions to find error handling patterns detected in the codebase, and get_architecture_review for structural context about the module. This ensures the refactor follows established project patterns. You: “Show me the drift alerts from the last week. What is causing our health score to drop?” Your AI assistant will call list_drift_alerts to retrieve recent regressions, showing exactly which PRs introduced which issues and how they affected category scores.

Security

MCP access through the Corbulo server is read-only. API keys used for MCP cannot:

Modify project settings
Trigger analyses or assessments
Access raw source code
Delete or dismiss issues
Manage team members or permissions

The MCP server exposes only aggregated analysis results, scores, and metadata. Source code is never transmitted through the MCP interface.

Getting Started

Core Features

Configuration

Integrations

Self-Hosting

MCP Integration

MCP Integration

Supported Tools

Setup

1. Create an API Key

2. Configure Your Tool

Available Tools

Project

Code Health

Analysis

Architecture

Pull Requests

Example Usage

Security

​MCP Integration

​Supported Tools

​Setup

​1. Create an API Key

​2. Configure Your Tool

​Available Tools

​Project

​Code Health

​Analysis

​Architecture

​Pull Requests

​Example Usage

​Security

MCP Integration

Supported Tools

Setup

1. Create an API Key

2. Configure Your Tool

Available Tools

Project

Code Health

Analysis

Architecture

Pull Requests

Example Usage

Security