mcp-scorecard audits an MCP server over stdio and assigns a 0-100 agent-readiness score based on 10 checks such as schema validity, tool naming, privacy mode documentation, annotations, resources, and discoverability. It can audit published npm packages, GitHub repos, local builds, or remote servers and output either human-readable text or JSON.
From the registry: Agent-readiness scorecard for any MCP server: 10 checks, 0-100 score, actionable findings.
Please install the `mcp-scorecard` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js and npm/npx** — Node.js is required to run the published npm package via npx. (https://nodejs.org/'}? սխ)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","mcp-scorecard","serve"]
Note: The README shows mcp-scorecard can be run as an MCP server using the published npm package. No environment variables are documented for the MCP server mode. The tool also supports auditing remote/hosted servers by URL as a target argument when invoked directly, but the MCP server install shape is stdio via `npx -y mcp-scorecard serve`.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MCP_PROBErequiredSet on the target server process so it can expose tools/resources/manifests without requiring auth during probing.MCP server for Gearsystem Sega Master System / Game Gear / SG-1000 emulator