Best for
- AI agents that require structured, typed output.
- Developers who need consistent behavior across environments without platform-specific quirks.
- Those looking to reduce token consumption and improve reliability.
P
Pare Make
Community
Structured Make/Just task runner operations (run, list) as typed JSON.
GitHub source repository ↗
25FMRS · D
Pare Make is a useful MCP server for converting make/just task execution into structured JSON, reducing agent parsing overhead. It is part of the larger Pare ecosystem, offering consistent output. However, it is a standalone server and does not include other Pare tools.
Pare Make is an MCP server within the Pare project that provides structured, typed JSON output for task runners such as make and just, replacing fragile text parsing. The server exposes two tools: run (execute a task) and list (enumerate available tasks). It returns schema-validated data via MCP's structuredContent, allowing AI agents to act on the data directly without parsing raw terminal output. It is published as the npm package @paretools/make and communicates over stdio.
Tools
run
Run a specified task in a Make or Just project, returning a structured result with fields like status, output, and error.
list
List available Make or Just targets, returning a structured list with fields such as name and description.
Setup
- Ensure Node.js >= 20 is installed.
- Add the following configuration to your MCP client:
{
"mcpServers": {
"pare-make": {
"command": "npx",
"args": ["-y", "@paretools/make"]
}
}
}
- Restart your MCP client session.
- Verify by running
npx -y @paretools/make.
claude_desktop_config.json
{
"mcpServers": {
"pare-make": {
"command": "npx",
"args": [
"-y",
"@paretools/make"
]
}
}
}
Fit and risk
Not for
- Users needing a graphical task-running interface.
- Projects that do not use make or just as their task runner.
- Environments with strict Node version requirements (requires Node >= 20).
Required permissions
- Execute tasks defined in Makefile or Justfile.
- Access project filesystem to locate and run tasks.
- May install dependencies or modify files, depending on task definitions.
Risks and side effects
- Arbitrary code execution: make and just tasks can run arbitrary shell commands.
- Permission abuse: if granted broad filesystem or network permissions, it could be misused.
- Token cost: although output is structured, listing many targets may still consume significant tokens.
Troubleshooting
- If you get npx or ENOENT errors, use `cmd /c npx` on Windows.
- If Node version is too old, upgrade to >= 20.
- If first start is slow, pre-run `npx -y @paretools/make` to cache, or install globally.
- If MCP connection times out, increase initTimeout in client config.
Use cases
Reliable task execution for development workflows without fragile text parsing.
Let AI agents obtain structured task lists and results from Make/Just directly.
Integrate task running into CI/CD or other automation scripts.
Supported clients
Claude DesktopFull support
Claude CodeFull support
CursorFull support
VS CodeFull support
WindsurfFull support