What does the get_last_build_status tool return?
It returns a JSON object with a `status` field (e.g., "completed" or "failed"), plus information about compiled files, warnings, duration, and any errors.
@Bigsy
Basic information
Read build information from shadow-cljs
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"shadow-cljs-mcp": {
"command": "npx",
"args": [
"shadow-cljs-mcp"
],
"disabled": false,
"autoApprove": [],
"timeout": 60
}
}
}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.
Shadow-cljs Mcp is a Model Context Protocol (MCP) server that monitors shadow-cljs builds and provides real-time build status updates. It connects to a running shadow-cljs instance, tracking build progress, failures, and completions, and is designed for LLMs used alongside ClojureScript development.
Install by adding the server configuration to your MCP client settings (e.g., Cline, Cursor, Claude) using the npx command. Optionally provide --host and --port arguments if your shadow-cljs instance is not on localhost:9630. After each ClojureScript file edit, instruct your LLM to call the get_last_build_status tool to verify the build succeeded. Add the tool call example to your LLM’s notes file (e.g., CLAUDE.md, cursorrules.md).
get_last_build_status tool.It returns a JSON object with a `status` field (e.g., "completed" or "failed"), plus information about compiled files, warnings, duration, and any errors.
Yes, Shadow-cljs Mcp connects to a running shadow-cljs instance. By default it expects it on localhost:9630, but you can override with `--host` and `--port`.
Add the provided JSON configuration to your MCP client’s settings, using the command `npx shadow-cljs-mcp`. No additional installation steps are required.
You can pass `--host` and `--port` to specify a different shadow-cljs server location. If omitted, defaults to localhost:9630.
Open-source MCP to use Blender with any LLM
Painless E2E Automation for Mobile and Web

Model Context Protocol Servers

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Comments