What does Mcplint check?
It checks name/schema validity, description quality, context-token weight, and destructive-tool safety.
@fletchert131-sudo
基本信息
Lint and score your MCP server's tool definitions before you publish — name/schema validity, description quality, context-token weight, and destructive-tool safety. Gives a 0–100 score and a CI gate. Free CLI, MIT engine. Catches structure and hygiene, not intent.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcplint": {
"command": "npx",
"args": [
"-y",
"-p",
"@tomfletcher2929/mcplint",
"mcplint-mcp"
]
}
}
}Lint and score an MCP tools payload (a tools array, or a tools/list result envelope) for name/schema validity, description quality, token weight, and safety annotations. Use before publishing an MCP server to check its tool definitions, or to grade another server's tools you fetched via tools/list.
Mcplint is a free, MIT-licensed CLI tool that lints and scores MCP server tool definitions before publication. It checks name/schema validity, description quality, context-token weight, and destructive-tool safety, outputting a 0–100 score and a CI gate.
Install and run the Mcplint CLI against your MCP server’s tool definitions. It returns a numeric score and can be integrated as a CI quality gate.
It checks name/schema validity, description quality, context-token weight, and destructive-tool safety.
It produces a 0–100 score.
Yes, it provides a CI gate.
MIT.
No, it catches structure and hygiene, not intent.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
评论