# Trustabl

Trustabl examines agent code for reliability and safety issues, then helps apply fixes. Scans run locally on your machine.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 79
- Author: trustabl
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/trustabl/agent-reliability-analyzer
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/trustabl

## What it does

Trustabl inspects an agent repository for issues such as unclear tool descriptions, missing retry or timeout handling, parameters without types, absent safeguards, and tool permissions beyond the agent’s stated tasks. Results can be shown as readable text, JSON, or SARIF.

The MCP server runs locally through Docker. Scanning needs no API key or network connection; applying changes requires your own Anthropic, OpenAI, or Google key. Docker is required for the Claude Code setup command.

Coverage spans nine SDKs and seven languages, including Claude Agent SDK, OpenAI Agents SDK, Google ADK, and MCP servers. Use it to review an agent project before deployment and make changes in its source code based on the scan.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add trustabl -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.12
```

### Codex

**Platform CLI**
```bash
codex mcp add trustabl -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.12
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "trustabl": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/trustabl/agent-reliability-analyzer:0.1.12"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "trustabl": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/trustabl/agent-reliability-analyzer:0.1.12"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add trustabl docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.12
```

## When to use it
- spot vague descriptions for agent tools
- catch missing retries and timeout handling
- check parameter types and safeguards
- find tool permissions beyond an agent’s tasks
- apply scan-driven changes to agent source code

## Example prompts
- Scan this repository for reliability and safety issues in its agent code.
- Check whether tool descriptions are clear and parameters have types.
- Review the agent’s tool permissions and suggest source-code fixes.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [mcp](https://affpapa.org/en/nevibecode/mcp/kubeshark-mcp.md) — MCP server · ★ 12109
- [Robin: AI-Powered Dark Web OSINT](https://affpapa.org/en/nevibecode/mcp/robin-ai-powered-dark-web-osint.md) — MCP server · ★ 7658
- [jshookmcp](https://affpapa.org/en/nevibecode/mcp/jshookmcp.md) — MCP server · ★ 2061
- [OpenOSINT](https://affpapa.org/en/nevibecode/mcp/openosint.md) — MCP server · ★ 1802

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md