Execute and list Make or Just tasks as structured JSON through a typed interface. For developers automating build pipelines and task orchestration in AI-assisted workflows.
io.github.Dave-London/pare-make
Local install
STDIO
No auth required
How models use it and what it is built for.
Execute and list Make or Just tasks as structured JSON through a typed interface. For developers automating build pipelines and task orchestration in AI-assisted workflows.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Dave London Pare Make.
Paste any of these into Agent Studio after connecting Dave London Pare Make.
Common questions about connecting and running Dave London Pare Make.
What build systems does Pare Make support?
Pare Make supports both Make and Just task runners. It provides structured JSON output for both run and list operations, allowing programmatic access to your build tasks.
How do I install and use Pare Make?
Install via `npx @paretools/make@0.8.1`. The server communicates over stdio and exposes task operations as typed JSON, making it easy to integrate into MCP-compatible tools.
Can I get task output as structured data?
Yes. Pare Make returns task execution results as typed JSON, allowing you to parse and process build output programmatically rather than as raw text.
What operations are available?
The server supports two main operations: listing all available tasks in your Make or Just file, and running specific tasks with arguments, both returning structured JSON responses.
Does Pare Make require authentication or configuration?
No special authentication is needed. Pare Make operates on your local Make or Just files and requires only that you have the build tool installed on your system.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent Studio