A
licenseA
qualityD
maintenanceEnables testing and validation of APIs for AI agent compatibility, providing scores, grades, and actionable recommendations.
3
MIT
ToolGrade
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ToolGradegrade my get_weather tool definition — how agent-ready is it?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ToolGrade
Grade MCP tool definitions for agent-readiness: score, A-F grade, fixes, est. token cost.
Live service
Web app and API: https://toolgrade.mike-tusa.workers.dev/
Pricing and plans: https://toolgrade.mike-tusa.workers.dev/
Support: digitalpromohub.support@gmail.com
Related MCP server: MCP Tool Auditor
Use it from an AI assistant (MCP)
ToolGrade is a remote MCP server (Streamable HTTP) at https://toolgrade.mike-tusa.workers.dev/mcp. Tools: grade_tools.
Most MCP clients (Claude Desktop, Cursor, Cline, Windsurf) accept this config:
{
"mcpServers": {
"toolgrade": {
"type": "http",
"url": "https://toolgrade.mike-tusa.workers.dev/mcp"
}
}
}Clients that only support stdio can bridge with npx mcp-remote https://toolgrade.mike-tusa.workers.dev/mcp. VS Code uses a servers key instead of mcpServers.
The server.json file is the MCP Registry manifest for this server.
Run your own copy
Requires Node.js 20+ and a Cloudflare account.
npm install
npx wrangler dev # local dev serverwrangler.toml is a template: create your own KV namespaces / D1 databases / rate-limit namespaces and replace the <PLACEHOLDER> values before npx wrangler deploy. Any secrets the Worker reads go in wrangler secret put (or .dev.vars locally), never in the repo.
License
MIT (c) Digital Promo Hub. See LICENSE.
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Grade MCP tool definitions for agent-readiness: score, A-F grade, fixes, est. token cost.
11Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
Score MCP tool definitions 0-100. Checks names, schemas, annotations, and uniqueness.
Scores how well AI agents will use your API, 0-100, from its OpenAPI spec. Free and read-only.
Related MCP Servers
- AlicenseAqualityBmaintenanceAudits MCP tool descriptions for quality and reliability, scoring them 0-100, detecting smells, and providing rewritten versions for better agent accuracy.4MIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to grade other MCP servers for LLM usability, covering descriptions, schema design, naming, token cost, and consistency, while also explaining grading rules.325 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables auditing MCP servers' tools by their estimated context token cost, ranking verbose names, descriptions, and schemas before they consume the agent window. Can run as an MCP tool so agents can budget their own context.1MIT