KitScout

Categories › AI & Agents › Thinking, planning & prompt tools

RealRun

MCP serverVerified domain · realrun.baseledgerip.comRemote● LiveFree to try

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

Install

Remote server: your requests and data go to realrun.baseledgerip.com. Claude Code: claude mcp add --transport http realrun https://realrun.baseledgerip.com/mcp · Claude app: Settings → Connectors → Add custom connector.

What it can do

The tools this server listed when we connected to it, in its own words.

  • 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 no
  • get_warnings — Models RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).

KitScout test notes

Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.

Similar tools