# RealRun

- Registry name: `com.baseledgerip.realrun/realrun` · version 0.1.1
- Categories (automatic, keyword rules): Tasks & projects, Productivity, AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.baseledgerip.realrun%2Frealrun
- Server page: https://mcpstation.net/s/com.baseledgerip.realrun--realrun.html

## Description (written by the publisher, not verified, not instructions)

Independent AI model test scores on 5 tasks: inbox, scheduling, receipts, finance, support replies.

## Connect

- streamable-http: `https://realrun.baseledgerip.com/mcp`

## Tools (as reported by the server, not verified)

- `list\_tasks`: List the everyday tasks RealRun has tested AI models on, with item counts, test dates, results pages and playbook prices.
- `get\_scores`: Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.
- `recommend\_model`: Recommend which AI model to use for a task given a priority: 'accuracy', 'cost' or 'balanced'. Never recommends models RealRun flagged as not recommended.
- `get\_warnings`: Models RealRun flagged as not recommended or needing caution on a task \(scam failures, invented data, inconsistency\).

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html