The shadow-cljs-mcp server monitors shadow-cljs builds and provides real-time build status updates for LLM integration.
Monitor Build Status: Tracks build progress, failures, and completions in real-time
Get Build Details: Provides detailed information including compiled files, warnings, errors, and duration
LLM Integration: Offers a get_last_build_status tool for LLMs to verify build success after ClojureScript file edits
Customizable Configuration: Allows optional server location configuration via --host and --port arguments
Monitors shadow-cljs builds and provides real-time build status updates for ClojureScript files, including compilation success/failure status, compiled files, error details, and build metrics.
Connects to a running shadow-cljs instance to track build progress and enable verification of build status after code changes through the npm package shadow-cljs-mcp.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@shadow-cljs-mcp check if my last ClojureScript changes compiled successfully"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that monitors shadow-cljs builds and provides real-time build status updates.
Add the following to your Cline/Cursor/Claude whatever settings:
{
"mcpServers": {
"shadow-cljs-mcp": {
"command": "npx",
"args": [
"shadow-cljs-mcp"
],
"disabled": false,
"autoApprove": [],
"timeout": 60
}
}
}With optional server location
{
"mcpServers": {
"shadow-cljs-mcp": {
"command": "npx",
"args": [
"shadow-cljs-mcp",
"--host",
"localhost",
"--port",
"9630"
],
"disabled": false,
"autoApprove": [],
"timeout": 60
}
}
}The --host and --port arguments are optional. If not provided, the server will default to connecting to localhost:9630.
Related MCP server: clj-kondo MCP Server
This MCP server connects to a running shadow-cljs instance and tracks build progress, failures, and completions. It provides an MCP tool that LLMs can use to verify build status after making changes to ClojureScript files.
Add the following to your LLM's notes file (e.g., CLAUDE.md, cursorrules.md):
After any edits to ClojureScript files, use the shadow-cljs-mcp server's get_last_build_status tool to verify the build succeeded:
<use_mcp_tool>
<server_name>shadow-cljs-mcp</server_name>
<tool_name>get_last_build_status</tool_name>
<arguments>
{}
</arguments>
</use_mcp_tool>
This will show:
- Build status (completed/failed)
- Which files were compiled
- Any errors or warnings
- Build duration and metricsSuccessful build:
{
"status": "completed",
"resources": 317,
"compiled": 1,
"warnings": 0,
"duration": 0.609,
"compiledFiles": [
"path/to/your/file.cljs (505ms)"
]
}Failed build:
{
"status": "failed",
"message": "Build failed",
"details": {
// Error information
}
}LLMs should call get_last_build_status after each ClojureScript file edit
Compilation errors will be shown in detail for easy debugging
Successful builds show which files were compiled and how long they took
Make sure shadow-cljs is running before starting this server
Running shadow-cljs instance (defaults to localhost:9630 if not configured otherwise)
Get the status of the last shadow-cljs build including any warnings or errors. Call this after making edits to ClojureScript files to verify if the build succeeded or failed.
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.
The single tool name 'get_last_build_status' follows a clear verb_noun pattern, and there are no other tools to create inconsistency. The naming is straightforward and predictable.
A single tool is too few for a server's purpose, as it severely limits functionality and suggests an incomplete or overly narrow scope. This makes the server feel thin and underdeveloped.
The server is severely incomplete for a build tool domain. It only provides status checking, with no tools for initiating builds, managing configurations, handling dependencies, or other essential operations, creating significant gaps.
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
