# CodeScene MCP server

> Lets AI assistants run CodeScene Code Health reviews on a local codebase to find maintainability issues and technical debt.

- Repository: https://github.com/codescene-oss/codescene-mcp-server
- Page: https://hostedmcp.org/servers/codescene-oss/codescene-mcp-server
- Official: yes
- Transport: stdio
- Stars: 85
- Latest version: 1.1.0

## Install

### Claude Code

```sh
claude mcp add codescene-mcp-server -- npx -y @codescene/codehealth-mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "codescene-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@codescene/codehealth-mcp"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "codescene-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@codescene/codehealth-mcp"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"codescene-mcp-server","type":"stdio","command":"npx","args":["-y","@codescene/codehealth-mcp"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "codescene-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@codescene/codehealth-mcp"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add codescene-mcp-server -- npx -y @codescene/codehealth-mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.codescene-mcp-server]
command = "npx"
args = ["-y", "@codescene/codehealth-mcp"]
```

### Gemini CLI

```sh
gemini mcp add -s user codescene-mcp-server npx -- -y @codescene/codehealth-mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "codescene-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@codescene/codehealth-mcp"
      ]
    }
  }
}
```

## FAQ

### Do I need a CodeScene account to use the MCP?

The full feature set requires a CodeScene subscription, authenticated via login or a CS_ACCESS_TOKEN. Local Code Health analysis is available without a subscription through the standalone CodeScene Code Health MCP.

### Does the CodeScene MCP send my source code to the cloud?

No. The server runs fully locally and all analysis happens on your machine against your local repository; only analysis results are fetched from your own CodeScene account via REST.

### Which LLM models work best with the CodeScene MCP?

Any model your AI assistant supports can work, but frontier models such as Claude Sonnet deliver better rule adherence and refactoring quality than legacy models like GPT-4.1.

### How do I configure custom SSL certificates for the MCP server?

Set the REQUESTS_CA_BUNDLE environment variable to point to your internal CA certificate file in PEM format. SSL_CERT_FILE and CURL_CA_BUNDLE are supported as alternatives.

### How do I install the CodeScene MCP server?

You can install it via NPM/npx, Homebrew, the Windows installer, Docker, or as a plugin or extension for Claude Code, Claude Desktop and VS Code; a manual binary download is also available.
