# io.scorecard/mcp

> Use this tool when you need to evaluate and optimize Large Language Model (LLM) systems, as it provides access to the Scorecard API through the MCP server, accepting LLM inputs and returning performance scorecards and optimization recommendations. It solves problems related to LLM system assessment and improvement, enabling data-driven decisions. Ideal for use cases requiring LLM evaluation, fine-tuning, and deployment optimization.

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

## Description

MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.

## Trust

- **Trust score (0–1):** 0.82
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 2.1.1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.scorecard%2Fmcp)
- **Repository:** <https://github.com/scorecard-ai/scorecard-node>

## Use it

MCP endpoint published by the skill: `https://mcp.scorecard.io/mcp`

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": "io-scorecard-mcp"
    }
  }
}
```

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