Skip to content

Agent Radar

by zation · remote · no sign-in to list tools · v0.9.2 · published by GitHub user zation

Search, inspect, recommend, and explain rated AI tools through Agent Radar.

Changes · 1
CompareRegistry entry

4 tools: 1 change things and 3 only read.

Scanned Oct 21, 2026

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

claude mcp add --transport http agent-radar https://agent-radar.zation1.workers.dev/api/mcp

Findings

Matches of fixed checks, with the text they matched.

1 info

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_toolsRecommend known tools for a task using request-scoped LLM credentials when required.1 finding

    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.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...ols for a task using request-scoped LLM credentials when required."

      What this check looks for
    Description, as the server wrote it
    Recommend known tools for a task using request-scoped LLM credentials when required.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
Only reads 3Claude Code: allow
  • explain_ratingReturn rating dimensions, explanations, penalties, and boosts for one tool_id.No findings

    Why it is in this group

    • The name "explain_rating" says "explain": a word for reading.
    Description, as the server wrote it
    Return rating dimensions, explanations, penalties, and boosts for one tool_id.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • get_tool_cardReturn one Tool Card and its Rating Result by stable tool_id.No findings

    Why it is in this group

    • The name "get_tool_card" says "get": a word for reading.
    Description, as the server wrote it
    Return one Tool Card and its Rating Result by stable tool_id.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • search_toolsSearch Agent Radar Tool Cards by query text and optional type, tag, or risk filters.No findings

    Why it is in this group

    • The name "search_tools" says "search": a word for reading.
    Description, as the server wrote it
    Search Agent Radar Tool Cards by query text and optional type, tag, or risk filters.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true

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 0.9.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-radar https://agent-radar.zation1.workers.dev/api/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__agent-radar__search_tools",
      "mcp__agent-radar__get_tool_card",
      "mcp__agent-radar__explain_rating"
    ],
    "ask": [
      "mcp__agent-radar__recommend_tools"
    ],
    "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 agent-radar. Review it before you use it.