# Mandoline

> Use this tool when you need to systematically evaluate and improve language models through conversational interfaces, creating and managing custom metrics, and running evaluations on prompt-response pairs. It provides a comprehensive set of tools for AI development teams, featuring session management, API key-based authentication, and automatic environment context injection. The Mandoline MCP server offers direct access to Mandoline's LLM evaluation platform, enabling efficient tracking and improvement of language models.

Canonical page: https://skillsregistry.net/skills/mandoline  
JSON: https://api.skillsregistry.net/v1/skills/mandoline

## Description

This Mandoline MCP server, developed by Mandoline AI, provides AI assistants with direct access to Mandoline's LLM evaluation platform through a comprehensive set of tools for creating and managing custom metrics, running evaluations on prompt-response pairs, and retrieving evaluation results. Built with TypeScript and Express, it features session management with automatic cleanup, API key-based authentication, and tools for both individual and batch operations on metrics and evaluations. The implementation includes automatic environment context injection (client info, model names) and content hashing for evaluation tracking, making it particularly useful for AI development teams who need to systematically evaluate and improve their language models through conversational interfaces rather than traditional dashboards.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/mandoline)
- **Repository:** <https://github.com/mandoline-ai/mandoline-mcp-server>

## 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": "mandoline"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mandoline` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mandoline/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