clj-kondo-MCP
MCP ServerFree** - Clojure linter
Capabilities6 decomposed
clojure code linting via mcp protocol
Medium confidenceExposes clj-kondo linting capabilities through the Model Context Protocol (MCP), allowing AI models and tools to invoke static analysis on Clojure code without direct subprocess management. Implements MCP server transport layer that wraps clj-kondo's analysis engine, translating linting results into structured JSON responses that conform to MCP resource and tool schemas for seamless integration with Claude, other LLMs, and MCP-compatible clients.
Bridges clj-kondo (a mature Clojure linter) into the MCP ecosystem, enabling AI models to invoke linting as a first-class tool without subprocess management boilerplate. Uses MCP's resource and tool schemas to expose linting as callable functions rather than requiring models to parse raw CLI output.
Provides standardized MCP integration for Clojure linting, whereas direct clj-kondo CLI usage requires models to handle subprocess spawning and output parsing, and existing Clojure IDE plugins are editor-specific rather than AI-model-agnostic.
real-time clojure syntax and style validation
Medium confidencePerforms on-demand static analysis of Clojure code to detect syntax errors, style violations, and common mistakes using clj-kondo's rule engine. Parses Clojure source text, applies configurable linting rules (unused variables, incorrect function arity, deprecated APIs, etc.), and returns diagnostics with precise line/column positions and severity levels (error, warning, info). Configuration is read from .clj-kondo/config.edn if present, allowing per-project customization.
Exposes clj-kondo's mature rule engine (covering 100+ linting rules) through MCP, enabling AI models to validate Clojure code with the same rigor as IDE plugins, but in a model-agnostic, protocol-standardized way. Respects project-level .clj-kondo/config.edn for rule customization.
More comprehensive than regex-based linting and more accessible than requiring IDE integration; clj-kondo itself is the de-facto Clojure linter, so this MCP wrapper provides the industry standard in an AI-friendly format.
mcp tool schema exposure for clojure linting
Medium confidenceRegisters clj-kondo linting as a callable MCP tool with a defined JSON schema, allowing MCP clients (like Claude) to discover, invoke, and handle linting requests as first-class tool calls. Implements MCP's tools/list and tools/call handlers, translating tool invocation parameters (code text, file paths) into clj-kondo subprocess calls and marshaling results back as structured JSON responses. Enables natural language requests like 'lint this code' to be routed to the linting engine without explicit model prompting.
Implements MCP's tools/list and tools/call protocol handlers to expose clj-kondo as a discoverable, invokable tool. Uses JSON schema to describe tool parameters, enabling clients to understand and invoke linting without hardcoded knowledge of clj-kondo's CLI interface.
Standardizes linting as an MCP tool, making it discoverable and callable by any MCP client; direct clj-kondo CLI usage requires models to know the exact invocation syntax, whereas MCP schema-based discovery is self-documenting and client-agnostic.
configurable linting rule application
Medium confidenceRespects project-level .clj-kondo/config.edn configuration files to customize which linting rules are enabled, disabled, or configured with specific parameters. Reads configuration from the project directory, merges it with clj-kondo's defaults, and applies the resulting rule set during analysis. Supports rule-level configuration such as severity overrides, exclusion patterns, and rule-specific options (e.g., max function arity warnings).
Leverages clj-kondo's native configuration system (.clj-kondo/config.edn) to allow per-project rule customization without modifying the MCP server. Configuration is read at linting time, enabling teams to enforce project-specific standards.
Provides configuration flexibility comparable to IDE-based linting, whereas hardcoded linting rules would require server code changes to customize; respects the Clojure ecosystem's standard configuration format.
batch file and directory linting
Medium confidenceAccepts file paths or directory paths as input and performs linting on multiple Clojure files in a single MCP call. Recursively traverses directories, identifies .clj, .cljs, and .cljc files, and returns aggregated diagnostics for all files with file-level grouping. Enables efficient bulk analysis of codebases without requiring separate tool calls per file.
Wraps clj-kondo's batch analysis capability in MCP, allowing single tool calls to lint entire directories. Aggregates results with file-level grouping, enabling efficient codebase-wide analysis without per-file MCP overhead.
More efficient than invoking linting separately for each file; provides codebase-wide analysis in a single MCP call, reducing latency and simplifying client logic compared to manual file enumeration and sequential linting.
structured diagnostic output with severity levels
Medium confidenceReturns linting results as structured JSON with detailed diagnostic objects including file path, line number, column number, rule name, message, and severity level (error, warning, info). Each diagnostic is a discrete object with all metadata needed for programmatic handling, enabling clients to filter, sort, or aggregate violations by severity, rule type, or file. Severity levels align with LSP (Language Server Protocol) conventions for compatibility with IDE tooling.
Exposes clj-kondo's diagnostic output as structured JSON with LSP-compatible severity levels, enabling programmatic filtering and aggregation. Each diagnostic includes full metadata (file, line, column, rule name, message) for rich client-side handling.
More structured than raw CLI output; JSON format enables easy parsing and filtering, whereas plain-text linting output requires regex parsing and is fragile to format changes.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with clj-kondo-MCP, ranked by overlap. Discovered automatically through the match graph.
@mcp-contracts/cli
CLI tool for capturing and diffing MCP tool schemas
@toolspec/core
MCP tool schema linting and quality scoring engine
mcp-tool-lint
Static linter for MCP tool definitions — catch quality defects before deployment
mcp-schema-lint
CLI linter for MCP tool/resource schemas
mcp-lint
Lint MCP server tool schemas for cross-client compatibility + runtime preflight for agent tool calls
Clojars
** - Obtains latest dependency details for Clojure libraries.
Best For
- ✓Clojure developers using Claude or other MCP-compatible AI models
- ✓Teams building MCP servers that need Clojure code quality checks
- ✓AI agents that need to validate Clojure syntax and style during code generation workflows
- ✓Clojure developers integrating linting into AI-assisted coding workflows
- ✓Teams using Claude or MCP clients to generate or review Clojure code
- ✓Agents that need to validate generated Clojure before execution
- ✓MCP client developers integrating Clojure support
- ✓Teams using Claude with MCP servers for code review workflows
Known Limitations
- ⚠Limited to clj-kondo's rule set — cannot enforce custom linting rules not supported by clj-kondo
- ⚠Requires clj-kondo binary to be installed and available in PATH; no pure-JVM fallback
- ⚠MCP protocol overhead adds latency compared to direct clj-kondo CLI invocation
- ⚠No built-in caching of lint results across multiple invocations — each request re-analyzes code
- ⚠Cannot perform semantic analysis beyond clj-kondo's rule set (e.g., no type checking without external tools)
- ⚠Linting speed depends on clj-kondo's performance; large files may incur multi-second latency
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
About
** - Clojure linter
Categories
Alternatives to clj-kondo-MCP
Are you the builder of clj-kondo-MCP?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →