LabscoMCP early access ↗
abcpro1MCP SERVER

MCP CLI Catalog

Tells your coding agent which CLI tools exist on the machine, so it stops guessing what it can pipe.

by abcpro1 ↗Editors, Terminals & Local Dev EnvironmentCommunity

LABSCO SUMMARY

Discovery, not execution — and that is the point.

A coding agent is already good at chaining commands with pipes and filters; what it lacks is knowing that your internal search script exists at all. This publishes that list and gets out of the way, which keeps the tool surface small compared with wrapping every command as its own MCP tool.

What it is

A server that publishes your own command-line tools as MCP tool definitions. It never runs anything itself — the definitions only tell the model what is available and how to invoke it, and the agent's existing shell access does the work.

What you get

  • A JSON catalog file where each entry carries a name, a description and an optional usage hint
  • command to set the exact string to run when it differs from the tool name
  • Comments allowed in the catalog file, so you can annotate it
  • --config <path> or MCP_CLI_CATALOG_FILE to point at a catalog other than the default
  • Inspection with npx @modelcontextprotocol/inspector npx mcp-cli-catalog

Requirements

Run it as npx mcp-cli-catalog (package mcp-cli-catalog, version 0.1.0). No account and no key. Two things it needs from you: a catalog file — ~/.mcp-cli-catalog.json by default — and an agent that already has shell access, since the server does not execute commands.

Setup effort

One command — npx mcp-cli-catalog

See installation options