SA

scorecard-ai/scorecard-mcp

Developer toolsOfficial
8 stars 4 forks Quality 27 Trend 16NOASSERTION

Scorecard MCP Remote MCP Server

Overview

Connect Claude to Scorecard's AI evaluation platform through natural language conversations. Test, measure, and improve your AI systems without switching between tools. Add the Scorecard MCP server's remote URL https://mcp.scorecard.io/mcp to your MCP client, e.g. Claude or Cursor. See the full setup instructions for more info and local installation configuration. This remote MCP server implements the latest version of the Model Context Protocol server specification. It is built with: - for authentication, implementing the OAuth 2.0 Protected Resource Metadata specification for secure, standards-compliant authentication flows. - for auto-generated, type-safe MCP endpoints that stay in sync with the API specification. - for production-grade monitoring, error tracking, and performance insights.

README

Scorecard remote MCP server

Connect Claude to Scorecard’s AI evaluation platform through natural language conversations. Test, measure, and improve your AI systems without switching between tools.

Installation

Add the Scorecard MCP server’s remote URL https://mcp.scorecard.io/mcp to your MCP client, e.g. Claude or Cursor.

See the full setup instructions for more info and local installation configuration.

Technical Architecture

This remote MCP server implements the latest version of the Model Context Protocol server specification. It is built with:

  • Clerk for authentication, implementing the OAuth 2.0 Protected Resource Metadata specification for secure, standards-compliant authentication flows.
  • Stainless for auto-generated, type-safe MCP endpoints that stay in sync with the API specification.
  • Sentry for production-grade monitoring, error tracking, and performance insights.

What You Can Do

Ask Claude to help with AI evaluation tasks:

  • “Create a new project for evaluating my chatbot”
  • “Set up test cases for customer service scenarios”
  • “Configure accuracy and helpfulness metrics”
  • “Run an evaluation against my latest model”
  • “Show me the performance results”
View the full README on GitHub

Install

This server does not publish a one-line install command.

Open the repository installation guide New to MCP? Start with the mcpskill.org guide →