cli.directory

mcporter

Agent-readyLocal AIAI

Runtime and CLI for connecting to configured Model Context Protocol servers.

Runtime and CLI for connecting to configured Model Context Protocol servers. Built by Peter Steinberger.

Task fit

mcp workflows, tool server connections, and agent integrations from the terminal.

Lane

Set up coding agents, local models, and AI-first terminal workflows.

Operator brief

Use mcporter for mcp workflows, tool server connections, and agent integrations from the terminal.

Run `mcporter --help` and see what comes back.

Repository family

Peter Steinberger

First trust check

mcporter responds locally and is ready for the first real command.

Safe first loop

Install, verify, then run one real command.

Agent capability loop

Install command

$ npm i -g mcporter

Operator pack

Copy or export the working notes for this CLI before handing it to an agent.

Verify

$ mcporter --version

mcporter responds locally and is ready for the first real command.

First real command

$ mcporter --help

First steps

  1. 01Install mcporter.
  2. 02Run `mcporter --version` first.
  3. 03Start with `mcporter --help`.
  4. 04Install the CLI and any required runtime, model, or Python environment.

When to use / hold off when

Best for

mcp workflows, tool server connections, and agent integrations from the terminal.

Use this when

You need AI models and inference in both local dev and CI.

Hold off when

You don't work with AI models and inference.

Trust and constraints

trusted85/100
Install readyTrusted
JSON outputNo
Non-interactiveYes
CI-friendlyYes

Why operators pick it

  • mcporter fits local ai well, especially for mcp workflows, tool server connections, and agent integrations from the terminal.
  • 142,940 npm weekly downloads.
  • Easy to automate.

Constraints

  • Needs network access.
  • Output is mostly plain text.

Facts and links

Install withnpm
npm weekly downloads142.9K
GitHub stars3.2K
LicenseNOASSERTION
UpdatedMar 4, 2026
DocumentationOpenGitHubOpenWebsiteOpen