🦉 Trustwise MCP Server

Name: 🦉 Trustwise MCP Server
Author: trustwiseai

@trustwiseai

Repository

About 🦉 Trustwise MCP Server

Trustwise MCP servers.

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "trustwise": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "TW_API_KEY",
        "ghcr.io/trustwiseai/trustwise-mcp-server:latest"
      ],
      "env": {
        "TW_API_KEY": "<YOUR_TRUSTWISE_API_KEY>"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is 🦉 Trustwise MCP Server?

The Trustwise MCP Server is a Model Context Protocol (MCP) server that provides a suite of advanced evaluation tools for AI safety, alignment, and performance. It enables developers and AI tools to programmatically assess the quality, safety, and cost of LLM outputs using Trustwise's industry-leading metrics.

How to use 🦉 Trustwise MCP Server?

Install via Docker, then configure your MCP client (e.g., Claude Desktop or Cursor) with the env variables TW_API_KEY (required) and optionally TW_BASE_URL for a custom Trustwise instance. Use the provided JSON snippet to launch the container with the command docker run -i --rm -e TW_API_KEY ghcr.io/trustwiseai/trustwise-mcp-server:latest.

Key features of 🦉 Trustwise MCP Server

Provides 19 evaluation metrics covering safety, alignment, and performance.
Detects PII, prompt injection, toxicity, and refusal in responses.
Measures faithfulness, relevancy, clarity, tone, and formality.
Estimates carbon footprint and cost of model inference.
Integrates with MCP clients like Claude Desktop and Cursor.

Use cases of 🦉 Trustwise MCP Server

Evaluate the safety and reliability of LLM responses.
Measure alignment, clarity, and helpfulness of AI-generated content.
Estimate the carbon footprint and cost of model inference.
Integrate robust evaluation into AI pipelines, agents, or orchestration frameworks.

FAQ from 🦉 Trustwise MCP Server

What are the prerequisites for running the Trustwise MCP Server?

You need a Trustwise API Key (available at trustwise.ai) and Docker installed on your machine.

How do I configure it for Claude Desktop or Cursor?

Add the provided JSON snippet to your MCP client settings, setting TW_API_KEY in the env section. Optionally set TW_BASE_URL to point to a specific Trustwise instance.

What evaluation metrics does the server provide?

It offers 19 metrics, including faithfulness, answer relevancy, PII detection, prompt injection, summarization, clarity, formality, helpfulness, sensitivity, tone, toxicity, refusal, completion, adherence, stability, carbon, and cost.