# NL;NL Labs

NL;NL Labs is an MCP server for Claude Code that exposes daily AI model test results by job. An agent can compare models by job and date.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: nlnl-labs
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/nlnl-labs/mcp
- Updated: 2026-11-12
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/nlnl-labs

## What it does

The server gives an agent access to published AI model test results. It lists nine jobs and the models tested for each, returns the outside model currently picked for a job with its date and figures, and provides model histories or all results for a particular day.

Results are read from public files on nlnllabs.com and are not stored by the server. No account is needed. Tool calls log the tool name, job, model or date, calling app, and time; records are deleted after 12 months. The question and IP address are not logged.

## Requirements
- Remote server: `https://mcp.nlnllabs.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http results https://mcp.nlnllabs.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add nlnl-labs --url https://mcp.nlnllabs.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "nlnl-labs": {
            "url": "https://mcp.nlnllabs.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "nlnl-labs": {
            "type": "http",
            "url": "https://mcp.nlnllabs.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http nlnl-labs https://mcp.nlnllabs.com/mcp
```

## When to use it
- find which models were tested for a job
- see the outside model picked for a job and its figures
- review one model’s results across dates
- retrieve every model’s result for a given day

## Example prompts
- List the jobs and the models tested for each one.
- Which outside model is picked for this job, and what are its results?
- Show this model’s results by day for the selected job.

## Similar
- [ATOM Pricing Intelligence](https://affpapa.org/en/nevibecode/mcp/atom-pricing-intelligence.md) — MCP server · 4780 installs
- [RealRun](https://affpapa.org/en/nevibecode/mcp/realrun.md) — MCP server
- [Wever Labs Agentic Rails](https://affpapa.org/en/nevibecode/mcp/wever-labs-agentic-rails.md) — MCP server · 708 installs
- [runcomfy-cli](https://affpapa.org/en/nevibecode/skills/runcomfy-cli.md) — skill · 390900 installs
- [Roundtable](https://affpapa.org/en/nevibecode/mcp/roundtable.md) — MCP server · 2845 installs
- [lambda-labs-gpu-cloud](https://affpapa.org/en/nevibecode/skills/lambda-labs-gpu-cloud.md) — skill · 1100 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
