Clojure linter
A Model Context Protocol (MCP) server that provides clj-kondo linting capabilities for Clojure/ClojureScript/EDN files. Handy for Claude code and desktop where there are no built in linting capabilities. You may want to consider editing your CLAUDE.md asking it to lint after editing.
npx clj-kondo-mcp
or IDE config
{
"mcpServers": {
"clj-kondo": {
"command": "npx",
"args": ["clj-kondo-mcp"],
"disabled": false,
"autoApprove": []
}
}
}
Install clj-kondo: Make sure you have clj-kondo installed and available on your system PATH. See the installation instructions for your platform.
Install dependencies:
npm install
npm run build
node build/index.js
The server provides one tool:
lint_clojure - Lint Clojure/ClojureScript/EDN content
Parameters:
{
"file": "/absolute/path/to/file.clj", // Must be absolute path - can be a file, directory, or classpath
"configDir": "/absolute/path/to/config/dir", // Optional, must be absolute path if provided
"level": "warning" // Optional, defaults to error level
}
The file
parameter accepts:
lein classpath
clojure -Spath
Note: Both file and configDir parameters must be absolute paths since the MCP server runs as a separate process. Relative paths will not work correctly.
By default, clj-kondo will automatically look for configuration in the .clj-kondo
directory in the current and parent directories. You can override this by specifying the configDir
parameter to point to a specific configuration directory.
For more information about clj-kondo configuration, see the official documentation.
Add to your MCP settings file (for Cline, located at ~/Library/Application Support/Code - Insiders/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
):
{
"mcpServers": {
"clj-kondo": {
"command": "npx",
"args": ["clj-kondo-mcp"],
"disabled": false,
"autoApprove": []
}
}
}
For manual builds, use:
{
"mcpServers": {
"clj-kondo": {
"command": "node",
"args": ["build/index.js"],
"disabled": false,
"autoApprove": []
}
}
}
npm run build
npm run dev
Refines and structures prompts for large language models using the Anthropic API.
Integrates with Jenkins CI/CD systems for AI-powered insights, build management, and debugging.
Provides sarcastic and cynical code reviews from the perspective of a grumpy senior developer.
Generate and edit images using OpenAI's DALL-E models via the official Python SDK.
Validate and visualize chess positions using FEN notation.
An autonomous memory management system for Claude AI, featuring multi-provider LLM integration and a persistent memory database.
Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.
Evaluates product designs against Dieter Rams' 10 principles of good design.
Generates AI agent tools from Postman collections and requests using the Postman API.
Create and read feature flags, review experiments, generate flag types, search docs, and interact with GrowthBook's feature flagging and experimentation platform.