com.baseledgerip.realrun/realrun

up checked 2026-11-10T19:37:36.098Z

Unclaimed · Unverified

Publisher-provided title

RealRun

Publisher-provided description

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

Summary by lookupd

Lets an agent look up independent AI model test scores, warnings, and model recommendations for everyday tasks like inbox and scheduling.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http realrun https://realrun.baseledgerip.com/mcp

Codex, remote (streamable-http)

codex mcp add realrun --url https://realrun.baseledgerip.com/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "realrun": {
      "url": "https://realrun.baseledgerip.com/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

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).

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.baseledgerip.realrun/realrun.svg)](https://lookupd.com/servers/com.baseledgerip.realrun/realrun)