Skip to content

ToolGrade

by toolgrade.mike-tusa.workers.dev · remote · no sign-in to list tools · v0.1.2 · published by dev.workers.mike-tusa.toolgrade

Grade MCP tool definitions for agent-readiness: score, A-F grade, fixes, est. token cost.

Changes · 1
CompareRegistry entry

1 tool: 1 change things.

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 toolgrade https://toolgrade.mike-tusa.workers.dev/mcp

Tools

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

1 tool

Changes things 1Claude Code: ask
  • grade_toolsGrade MCP tool definitions (the tools array from a tools/list result) for how well AI agents can pick and call them.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
    Grade MCP tool definitions (the tools array from a tools/list result) for how well AI agents can pick and call them. Returns a 0–100 score and A–F grade, per-tool scores, and findings with concrete fixes: missing or weak descriptions, untyped parameters, strings without maxLength, missing required or additionalProperties, missing annotations (readOnlyHint, destructiveHint …), invalid or duplicate names, outputSchema and enum problems, hidden characters and tool-poisoning patterns. Also returns an ESTIMATED token cost of the definitions (characters ÷ 4; real counts vary by model). Pure parsing: no network calls, and your tool definitions are never stored. Read-only. Same engine as the ToolGrade JSON API (POST /api/grade).

    Annotations the server declares

    • title: Grade MCP tools
    • 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 0.1.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http toolgrade https://toolgrade.mike-tusa.workers.dev/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": [],
    "ask": [
      "mcp__toolgrade__grade_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 toolgrade. Review it before you use it.