Skip to main content
MCP server CX Codex

RealRun — Claude Code MCP server: model tests and setup

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.

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http realrun https://realrun.baseledgerip.com/mcp
Open on GitHub

What RealRun 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.

What it helps with

  • 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 for the agent

  • 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.

How to install RealRun

Platform CLI: remote server

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

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about RealRun

How do I install RealRun in Claude Code?

Run claude mcp add --transport http realrun https://realrun.baseledgerip.com/mcp. This connects to the remote server over HTTP.

What does RealRun do?

It provides scores and safety warnings from tests of AI models on inbox, scheduling, receipts, finance, and customer support tasks.

Which tasks can RealRun evaluate?

Its task IDs are inbox-triage, meeting-scheduling, receipts, finance, and support-replies. The server's tools only read data.

Similar MCP servers

All MCP servers for AI and ML →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor