# code-graph MCP server

> Lets an AI agent query a local dependency graph to identify how code changes affect routes, calls, tables, and configurations.

- Repository: https://github.com/cyberchronos00/code-graph
- Page: https://hostedmcp.org/servers/cyberchronos00/code-graph
- Transport: stdio
- Stars: 4
- License: MIT
- Latest version: 0.23.14

## Install

### Claude Code

```sh
claude mcp add code-graph -- uvx cg-code-graph
```

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

```json
{
  "mcpServers": {
    "code-graph": {
      "command": "uvx",
      "args": [
        "cg-code-graph"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "code-graph": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "cg-code-graph"
      ]
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "code-graph": {
      "command": "uvx",
      "args": [
        "cg-code-graph"
      ]
    }
  }
}
```

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

```toml
[mcp_servers.code-graph]
command = "uvx"
args = ["cg-code-graph"]
```

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

```json
{
  "mcpServers": {
    "code-graph": {
      "command": "uvx",
      "args": [
        "cg-code-graph"
      ]
    }
  }
}
```

## FAQ

### Does this use an LLM to build the graph?

No, the dependency graph is local and deterministic without using an LLM.

### Can it help with security auditing?

Yes, it can list the inbound and outbound attack surface and findings like hardcoded credentials or unguarded handlers.