Trustabl — Claude Code MCP server: checks and setup
Trustabl examines agent code for reliability and safety issues, then helps apply fixes. Scans run locally on your machine.
claude mcp add trustabl -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.12What Trustabl 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.
What it helps with
- 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 for the agent
- 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.
How to install Trustabl
Platform CLI
claude mcp add trustabl -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.12Platform CLI
codex mcp add trustabl -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.12Config file
{
"mcpServers": {
"trustabl": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/trustabl/agent-reliability-analyzer:0.1.12"
]
}
}
}Config file
{
"servers": {
"trustabl": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/trustabl/agent-reliability-analyzer:0.1.12"
]
}
}
}Platform CLI
gemini mcp add trustabl docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.12Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Trustabl
How do I install Trustabl in Claude Code?
Run claude mcp add trustabl -- docker run -i --rm ghcr.io/trustabl/agent-reliability-analyzer:0.1.12. Docker is needed to launch the server.
What does Trustabl do?
It scans agent code for reliability and safety problems, including missing timeouts, untyped parameters, and excessive tool permissions. It can also help apply fixes to the source.
Does scanning require an API key?
No. Scanning runs locally without a key or network access. Applying fixes requires your own Anthropic, OpenAI, or Google key.
