# Trustabl MCP server

> Finds and fixes reliability and safety gaps in AI agent code across nine SDKs using deterministic static analysis.

- Repository: https://github.com/trustabl/agent-reliability-analyzer
- Page: https://hostedmcp.org/servers/trustabl/agent-reliability-analyzer
- Transport: stdio
- Stars: 88
- License: Apache-2.0
- Latest version: 0.1.16

## Install

### Claude Code

```sh
claude mcp add agent-reliability-analyzer -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.16
```

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

```json
{
  "mcpServers": {
    "agent-reliability-analyzer": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/trustabl/agent-reliability-analyzer:0.1.16"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "agent-reliability-analyzer": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/trustabl/agent-reliability-analyzer:0.1.16"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"agent-reliability-analyzer","type":"stdio","command":"docker","args":["run","-i","--rm","ghcr.io/trustabl/agent-reliability-analyzer:0.1.16"]}'
```

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

```json
{
  "mcpServers": {
    "agent-reliability-analyzer": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/trustabl/agent-reliability-analyzer:0.1.16"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add agent-reliability-analyzer -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.16
```

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

```toml
[mcp_servers.agent-reliability-analyzer]
command = "docker"
args = ["run", "-i", "--rm", "ghcr.io/trustabl/agent-reliability-analyzer:0.1.16"]
```

### Gemini CLI

```sh
gemini mcp add -s user agent-reliability-analyzer docker -- run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.16
```

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

```json
{
  "mcpServers": {
    "agent-reliability-analyzer": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/trustabl/agent-reliability-analyzer:0.1.16"
      ]
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `ANTHROPIC_API_KEY` | no | no |  |
| `CGO_ENABLED` | no | no |  |
| `COSIGN_PASSWORD` | no | no |  |
| `LANGSMITH_API_KEY` | no | no |  |
| `OPENAI_BASE_URL` | no | no |  |
| `TRUSTABL_LLM_MODEL` | no | no |  |
| `TRUSTABL_TELEMETRY` | no | no |  |

## Tools (2)

- `scan`: Scan a local directory or repository for AI-agent security misconfigurations with Trustabl. Returns the structured scan result (findings, scores, and discovered inventory) as JSON.
- `version`: Report the Trustabl build version, commit, and build date.

## FAQ

### Does the scanner require an internet connection or cloud upload?

No, the scanner runs entirely on your local machine with no cloud scanner, no account, no code upload, and no LLM required for the scan.

### What kind of output formats does the tool support?

The tool supports human-readable, JSON, and SARIF 2.1.0 output formats.
