Skip to main content
Glama
enesjakozh
Bigsy

clj-kondo MCP Server

by Bigsy
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

clj-kondo MCP Server npm version

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.

Features

  • Lint Clojure files via MCP tool calls

  • Supports all clj-kondo analysis capabilities

  • Optional explicit configuration directory support

Related MCP server: shadow-cljs-mcp

Installation

Quick Install

npx clj-kondo-mcp

or IDE config

{
  "mcpServers": {
    "clj-kondo": {
      "command": "npx",
      "args": ["clj-kondo-mcp"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

Manual Installation

  1. Install clj-kondo: Make sure you have clj-kondo installed and available on your system PATH. See the installation instructions for your platform.

  2. Install dependencies:

npm install

  1. Build the server:

npm run build

Usage

Running the Server

node build/index.js

MCP Tool Calls

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:

  • A single file path (e.g. "/path/to/src/my_file.clj")

  • A directory path (e.g. "/path/to/src") - will lint all .clj, .cljs and .cljc files recursively

  • A classpath string - will lint all Clojure files in the classpath

    • For Leiningen projects: Use output of lein classpath

    • For deps.edn projects: Use output of 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.

Configuration

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": []
    }
  }
}

Build

npm run build

Watch Mode

npm run dev

Available Tools

1 tool
lint_clojureA

Lint Clojure/ClojureScript/EDN content using clj-kondo

ParametersJSON Schema
NameRequiredDescriptionDefault
configDirNoOptional absolute path to .clj-kondo config directory (e.g. /Users/name/project/.clj-kondo). If not provided, clj-kondo will look for .clj-kondo directory in the current and parent directories.
fileYesCan be: 1) Absolute path to a file, 2) Directory path (will lint all .clj/.cljs/.cljc files recursively), or 3) Classpath string (obtained via `lein classpath` or `clojure -Spath`)
levelNoOptional linting level. By default all lints are errors. Set to "warning" to use warning level instead.

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It specifies what gets processed (Clojure/ClojureScript/EDN content) and the tool used, but doesn't describe output format, error handling, performance characteristics, or what constitutes successful linting. The description adds some value but leaves significant behavioral aspects undocumented.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that communicates the essential purpose without any wasted words. It's front-loaded with the core functionality and uses precise terminology. Every element of the description earns its place by adding meaningful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and 3 parameters with good schema coverage, the description provides adequate basic context but leaves gaps. It explains what the tool does but doesn't describe what users can expect as results, how to interpret linting output, or any limitations of the clj-kondo approach. For a tool with no structured output documentation, more guidance would be helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the baseline is 3. The description adds value by providing context about what 'lint' means in this context and specifying the exact tool being used (clj-kondo), which helps users understand the linting approach and standards being applied beyond what the parameter descriptions provide.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verb ('lint') and target resources ('Clojure/ClojureScript/EDN content'), and specifies the implementation method ('using clj-kondo'). It distinguishes itself by naming the exact linter being used, which is helpful even without sibling tools for comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides implied usage context by specifying what types of content can be linted and the tool being used, but offers no explicit guidance on when to use this tool versus alternatives (though no sibling tools exist). It doesn't mention prerequisites, typical workflows, or integration scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool has a single, clear purpose that is distinct by default.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The naming follows a clear verb_noun pattern (lint_clojure).

Tool Count2/5

A single tool is too few for a server's purpose, as it limits functionality and suggests an incomplete or overly narrow scope. Typically, servers benefit from multiple tools to cover various operations within their domain.

Completeness2/5

The server only provides linting, which is a significant gap for a tool named after clj-kondo, as it might be expected to support other related operations like configuration management or analysis. The surface is severely incomplete for a comprehensive Clojure tooling server.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • MCP Tools

    ZbigniewTomanek
    A
    license
    Not graded
    quality
    D
    maintenance
    A custom Model Context Protocol server that gives Claude Desktop and other LLMs access to file system operations and command execution capabilities through standardized tool interfaces.
    23
    Apache 2.0

  • shadow-cljs-mcp

    Bigsy
    A
    license
    A
    quality
    D
    maintenance
    A Model Context Protocol server that monitors shadow-cljs builds and provides real-time build status updates for ClojureScript projects, allowing LLMs to verify build status after making code changes.
    1
    24
    3
    MIT

  • Tafa MCP Server

    N3uraX
    A
    license
    Not graded
    quality
    D
    maintenance
    A production-ready Model Context Protocol server that provides comprehensive file system management capabilities for seamless integration with Claude Desktop.
    1
    MIT

  • Codebase MCP Server

    cmaujean
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that analyzes application codebases with real-time file watching, providing AI assistants like Claude with deep insights into project structure, code patterns, and architecture.
    MIT

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Bigsy/clj-kondo-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server