ToolGrade
Grade MCP tool definitions for agent-readiness: score, A-F grade, fixes, est. token cost.
사용해야 할까요
품질 및 안전성
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"toolgrade": {
"url": "https://toolgrade.mike-tusa.workers.dev/mcp"
}
}
}원격 엔드포인트
https://toolgrade.mike-tusa.workers.dev/mcpstreamable-http할 수 있는 일
도구 목록
도구 (1)
🟢grade_tools(tools, tools_json, include_raw)
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).
입력 스키마
{
"type": "object",
"properties": {
"tools": {
"type": "array",
"minItems": 1,
"maxItems": 200,
"description": "The tool definitions to grade, e.g. [{\"name\": \"search_docs\", \"description\": \"...\", \"inputSchema\": {...}}]: the \"tools\" array of a tools/list result. Up to 200 tools. Provide this or tools_json.",
"items": {
"type": "object",
"description": "One MCP tool definition (name, description, inputSchema, optional title, annotations, outputSchema)."
}
},
"tools_json": {
"type": "string",
"minLength": 1,
"maxLength": 262144,
"description": "Alternative to tools: raw JSON text of a tools/list response, its result object ({\"tools\": [...]}) or a tool array, exactly as copied."
},
"include_raw": {
"type": "boolean",
"default": false,
"description": "Also return the full /api/grade report (all findings and every tool row) in structuredContent.raw. Larger output."
}
},
"required": [],
"additionalProperties": false
}출력 스키마
{
"type": "object",
"properties": {
"score": {
"type": "number"
},
"grade": {
"type": "string",
"enum": [
"A",
"B",
"C",
"D",
"F"
]
},
"toolCount": {
"type": "number"
},
"critical": {
"type": "number"
},
"warning": {
"type": "number"
},
"info": {
"type": "number"
},
"verdictMeaning": {
"type": "string"
},
"estimatedTokens": {
"type": "number",
"description": "ESTIMATED total token cost of all definitions (compact JSON chars ÷ 4)."
},
"tokenNote": {
"type": "string"
},
"tools": {
"type": "array",
"items": {
"type": "object",
"properties": {
"index": {
"type": "number"
},
"name": {
"type": "string"
},
"score": {
"type": "number"
},
"grade": {
"type": "string",
"enum": [
"A",
"B",
"C",
"D",
"F"
]
},
"estimatedTokens": {
"type": "number"
},
"critical": {
"type": "number"
},
"warning": {
"type": "number"
},
"info": {
"type": "number"
}
},
"required": [
"index",
"name",
"score",
"grade",
"estimatedTokens"
]
}
},
"toolsOmitted": {
"type": "number"
},
"findings": {
"type": "array",
"items": {
"type": "object",
"properties": {
"severity": {
"type": "string",
"enum": [
"critical",
"warning",
"info"
]
},
"code": {
"type": "string"
},
"tool": {
"type": "string",
"description": "Tool name (from the submitted input; untrusted). Omitted for server-wide findings."
},
"path": {
"type": "string"
},
"count": {
"type": "number"
},
"message": {
"type": "string"
},
"fix": {
"type": "string"
}
},
"required": [
"severity",
"code",
"message",
"fix"
]
}
},
"findingsOmitted": {
"type": "number"
},
"version": {
"type": "string"
},
"raw": {
"type": "object",
"description": "Full /api/grade response (only when include_raw is true)"
}
},
"required": [
"score",
"grade",
"toolCount",
"estimatedTokens",
"tools",
"findings",
"version"
]
}커뮤니티
증거