Skip to content

RealRun

by realrun.baseledgerip.com · remote · no sign-in to list tools · v0.1.1 · published by com.baseledgerip.realrun

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

Changes · 1
CompareRegistry entry

4 tools: 1 change things and 3 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 1Claude Code: ask
  • recommend_modelRecommend which AI model to use for a task given a priority: 'accuracy', 'cost' or 'balanced'.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Recommend which AI model to use for a task given a priority: 'accuracy', 'cost' or 'balanced'. Never recommends models RealRun flagged as not recommended.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
Only reads 3Claude Code: allow
  • get_scoresHeadline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.No findings

    Why it is in this group

    • The name "get_scores" says "get": a word for reading.
    Description, as the server wrote it
    Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_warningsModels RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).No findings

    Why it is in this group

    • The name "get_warnings" says "get": a word for reading.
    Description, as the server wrote it
    Models RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_tasksList the everyday tasks RealRun has tested AI models on, with item counts, test dates, results pages and playbook prices.No findings

    Why it is in this group

    • The name "list_tasks" says "list": a word for reading.
    Description, as the server wrote it
    List the everyday tasks RealRun has tested AI models on, with item counts, test dates, results pages and playbook prices.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__realrun__list_tasks",
      "mcp__realrun__get_scores",
      "mcp__realrun__get_warnings"
    ],
    "ask": [
      "mcp__realrun__recommend_model"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as realrun. Review it before you use it.