# agent-graph-auditor MCP server

> Identifies transitive excessive agency in multi-agent orchestration graphs by detecting indirect paths to dangerous tools.

- Repository: https://github.com/GuardBee/guardbee-mcp
- Page: https://hostedmcp.org/servers/guardbee/agent-graph-auditor
- Transport: stdio
- Stars: 2
- License: MIT
- Latest version: 0.1.2

## Install

### Claude Code

```sh
claude mcp add agent-graph-auditor -- npx -y @guardbee/mcp-agent-graph-auditor
```

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

```json
{
  "mcpServers": {
    "agent-graph-auditor": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-agent-graph-auditor"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "agent-graph-auditor": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-agent-graph-auditor"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"agent-graph-auditor","type":"stdio","command":"npx","args":["-y","@guardbee/mcp-agent-graph-auditor"]}'
```

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

```json
{
  "mcpServers": {
    "agent-graph-auditor": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-agent-graph-auditor"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add agent-graph-auditor -- npx -y @guardbee/mcp-agent-graph-auditor
```

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

```toml
[mcp_servers.agent-graph-auditor]
command = "npx"
args = ["-y", "@guardbee/mcp-agent-graph-auditor"]
```

### Gemini CLI

```sh
gemini mcp add -s user agent-graph-auditor npx -- -y @guardbee/mcp-agent-graph-auditor
```

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

```json
{
  "mcpServers": {
    "agent-graph-auditor": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-agent-graph-auditor"
      ]
    }
  }
}
```

## Tools (4)

- `scan_text`: Scan a Python snippet defining a multi-agent orchestration (LangGraph, CrewAI, or AutoGen/ag2) for excessive agency reachable through delegation or group membership — an agent with no dangerous tool of its own that can still reach one (shell/code-exec/file-write/network/credentials) through another agent it can hand off to.
- `scan_file`: Scan a single Python file for excessive-agency paths across LangGraph/CrewAI/AutoGen orchestration constructs
- `scan_directory`: Recursively scan a directory of Python files and report excessive-agency paths found in each. Each file's agent/tool graph is analyzed independently — variable references don't resolve across files, so a Crew/GroupChat whose members are defined in a different file than the assembling call won't be connected.
- `list_patterns`: List every dangerous-capability rule this auditor looks for at the end of a delegation path, grouped by category

## FAQ

### How does it handle telemetry?

Telemetry is disabled by default; you can enable it using the GUARDBEE_TELEMETRY=1 environment variable.

### Can it scan across multiple files?

No, the scanner has a single-file scope where each file's graph is extracted independently, meaning variable references do not resolve across files.

### What kind of output does it provide?

The server provides SARIF 2.1.0 output, which allows for integration with CI/CD tools like GitHub Code Scanning.
