Skip to content

runx

by runx.ai · remote · no sign-in to list tools · v1.0.0 · published by ai.runx

The governed runtime for agent skills. Search the catalog and inspect a skill before running it.

Read only
CompareRegistry entry

2 tools: 2 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 runx https://api.runx.ai/mcp

Tools

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

2 tools

Only reads 2Claude Code: allow
  • get_skillRead one runx skill in full before running it: its manifest, the authority it asks for, its publisher and trust signals, and the exact command to install and run it through the run…No findings

    Why it is in this group

    • The name "get_skill" says "get": a word for reading.
    Description, as the server wrote it
    Read one runx skill in full before running it: its manifest, the authority it asks for, its publisher and trust signals, and the exact command to install and run it through the runx CLI. Everything needed to decide whether to trust a skill arrives in this one call.

    Annotations the server declares

    • title: Inspect runx skill
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_skillsFind runx skills by what they do.No findings

    Why it is in this group

    • The name "search_skills" says "search": a word for reading.
    Description, as the server wrote it
    Find runx skills by what they do. Returns each match with its skill id, owner, description, latest version, and trust tier, so a caller can pick one and then read it in full with get_skill.

    Annotations the server declares

    • title: Search runx skills
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: 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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http runx https://api.runx.ai/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__runx__search_skills",
      "mcp__runx__get_skill"
    ],
    "ask": [],
    "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 runx. Review it before you use it.