Mcplint
About
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.
Details
- Author
- fletchert131-sudo
- Downloads
- 313
- Categories
- Developer Tools
Jump to
- Checks name and schema validity
- Evaluates description quality
- Analyzes context-token weight
- Assesses destructive-tool safety
- Produces a 0–100 score
- Provides a CI gate
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
McplintCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
lint_tools
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcplint": {
"mcplint": {
"command": "npx",
"args": [
"-y",
"-p",
"@tomfletcher2929/mcplint",
"mcplint-mcp"
]
}
}
}
}McpServers
{
"mcplint": {
"command": "npx",
"args": [
"-y",
"-p",
"@tomfletcher2929/mcplint",
"mcplint-mcp"
]
}
}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.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
