ToolGrade MCP Server

by workers-mike-tusa-toolgrade Your server? Claim it

answering

ToolGrade is answering right now. Last checked moments ago. It exposes 1 tools.

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

Uptime history 9 days of history

9 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

158 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 18 October 2026. No other catalogue keeps this.

18 Oct a tool changed version

Nothing serious here today

Today is the operative word: we check ToolGrade every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add toolgrade --transport http https://toolgrade.mike-tusa.workers.dev/mcp

Settings → Connectors → Add custom connector, then paste this address

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

~/.codex/config.toml

[mcp_servers.toolgrade]
url = "https://toolgrade.mike-tusa.workers.dev/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "toolgrade": {
      "url": "https://toolgrade.mike-tusa.workers.dev/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "toolgrade": {
      "type": "http",
      "url": "https://toolgrade.mike-tusa.workers.dev/mcp"
    }
  }
}

Available tools 1

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

grade

grade_tools

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).

Endpoints

URL	Transport	State	Latency	Checked
https://toolgrade.mike-tusa.workers.dev/mcp	streamable-http	answering	93 ms	0 min ago

Alternatives to ToolGrade

same job, measured the same way

MCP Scorecard

by davidmosiah

Agent-readiness scorecard for any MCP server: 10 checks, 0-100 score, actionable findings.

52 installs/wk local only

Scbee MCP

by hmakt99

Score repos for launch and agent readiness, find verified agents, read collaborations. Read-only.

28 installs/wk local only

Semantic Cache MCP

by coderdayton

File cache for coding agents: re-reads cost ~40 tokens, changed files return diffs.

690 installs/wk local only

MCP Validator

by wildrunai

Score MCP tool definitions 0-100. Checks names, schemas, annotations, and uniqueness.

answering

Agentready

by vercel-agentready-rho

Scan any website or MCP server for agent readiness: 0-100 score, a fix per failing check. Free.

11 tools answering

Tool Poisoning Scanner

by guardbee

Scans MCP tool definitions for hidden instructions and confused-deputy sinks

1 081 installs/wk local only

Tool Poisoning Scanner

by 4hmetuyar

Scans MCP tool definitions for hidden instructions and confused-deputy sinks

local only

MCP Cost Tracker Router

by dbsectrainer

Real-time cost awareness for MCP agent workflows

16 installs/wk local only

ToolGrade — questions

Answers built from our own checks of this server.

What can ToolGrade do?

It exposes 1 tools, read directly from the server on our last check. Among them: grade_tools. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is ToolGrade working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 158 ms. The bar chart above shows every period we have measured.

How do I connect ToolGrade?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does ToolGrade need an API key?

No. ToolGrade completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 1 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is ToolGrade?

It answers our handshake in 158 ms on average, which is faster than 87% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.