# RealRun

RealRun serves scores and safety flags from independent AI model tests on everyday work. Use it to compare models for inbox, scheduling, receipts, finance, or support tasks.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: baseledgerip
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/baseledgerip/realrun-mcp
- Updated: 2026-10-17
- HTML: https://affpapa.org/en/nevibecode/mcp/realrun

## What it does

RealRun lets an agent compare models tested on inbox triage, meeting scheduling, receipts, small-business finance, and customer support replies. `get_scores` returns model scores and cost tiers; `recommend_model` selects an option based on accuracy, cost, or balance, while `get_warnings` surfaces cautions such as fabricated data or scam failures.

Connect over remote HTTP with `claude mcp add --transport http realrun https://realrun.baseledgerip.com/mcp`. For local use, run `npx -y realrun-mcp` once the package is published, or use `npm install && node src/stdio.mjs` from a checkout. The tools are read-only, and test scores describe results from the dates shown rather than guaranteeing how a model will perform in your project.

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

## Install

### Claude Code (native platform)

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

### Codex

**Platform CLI: remote server**
```bash
codex mcp add realrun --url https://realrun.baseledgerip.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "realrun": {
            "url": "https://realrun.baseledgerip.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "realrun": {
            "type": "http",
            "url": "https://realrun.baseledgerip.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http realrun https://realrun.baseledgerip.com/mcp
```

## When to use it
- compare models for inbox triage
- choose a meeting scheduler with cost as the priority
- check finance-task results for warnings about fabricated data
- review model scores for customer support replies

## Example prompts
- Compare models for inbox triage and show their scores.
- Recommend a meeting-scheduling model with cost as the priority.
- Show the warnings for the receipts task.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
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