# Scorecard MCP Server

> Use this tool when you need to integrate Scorecard's evaluation tools with MCP-compatible clients, such as Claude, to run experiments, generate synthetic data, and analyze model performance. It solves problems related to model testing and validation by providing a secure and scalable server solution that can be deployed on Cloudflare Workers. The Scorecard MCP Server accepts authentication inputs through Clerk and outputs evaluation results, making it ideal for use cases that require robust model evaluation and analysis.

Canonical page: https://skillsregistry.net/skills/evolv3ai-scorecard-mcp  
JSON: https://api.skillsregistry.net/v1/skills/evolv3ai-scorecard-mcp

## Description

Enables Claude and other MCP-compatible clients to access Scorecard's evaluation tools for running experiments, generating synthetic data, and analyzing model performance. It is designed to be deployed on Cloudflare Workers and integrates securely with Scorecard's API using Clerk for authentication.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/lbv2hd5gih)
- **Repository:** <https://github.com/evolv3ai/scorecard-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "evolv3ai-scorecard-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/evolv3ai-scorecard-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/evolv3ai-scorecard-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt