본문으로 건너뛰기
cccskills
무료GitHub에 공개

mcporter

Discover and call configured MCP server tools through the mcporter command line. Inspect the inputs each tool accepts, invoke external services, and create SKILL.md reference guides with usage examples for newly added servers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Discover and call MCP Server tools via the mcporter CLI. Use when your coordinator notifies you about new MCP tools, or when you need to call external APIs. Includes workflow for generating skill documentation for new MCP servers.

설치 방법 보기

이럴 때 유용합니다

  • List tools available on configured MCP servers
  • Call external services with tool arguments
  • Create SKILL.md guides for new MCP servers
  • Refresh configuration after new tools are added

포함된 파일(1)

  • SKILL.md3.7 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

mcporter — MCP Tool CLI

You call MCP Server tools via mcporter. Your config is at ./config/mcporter.json (mcporter's default path — no --config flag needed).

Commands

# List all configured MCP servers and their tool counts
mcporter list

# View a specific server's tools with full parameter schemas
mcporter list <server-name> --schema

# Call a tool — key=value syntax for simple args
mcporter call <server-name>.<tool-name> key=value key2=value2

# Call a tool — JSON syntax for complex args (arrays, objects, numbers)
mcporter call <server-name>.<tool-name> --args '{"key":"value","count":5}'

Output is JSON — parse with jq when needed.

When Your Coordinator Notifies You About New MCP Tools

When your coordinator @mentions you saying a new MCP server has been configured, follow this workflow:

Step 1: Pull the updated config

Use the filesync tool to pull the latest config files:

{
  "action": "pull",
  "path": "shared/"
}

Step 2: Discover the new server and its tools

# Verify the new server appears
mcporter list

# Get full tool schemas — read carefully to understand each tool
mcporter list <server-name> --schema

Step 3: Generate a skill for the new MCP server

After understanding the tools, create a skill directory and SKILL.md so you have a permanent reference. Model it after your github-operations skill:

mkdir -p ~/skills/<server-short-name>-operations

Then write ~/skills/<server-short-name>-operations/SKILL.md with:

  1. Front-matter: name, description, assign_when
  2. Overview section explaining what the MCP server does
  3. For each tool: a section with description, example mcporter call command, and parameter notes
  4. Important notes (rate limits, auth, known issues if any)

Use the tool schemas from Step 2 as the source of truth for parameter names, types, and required/optional status.

Example structure:

---
name: weather-operations
description: Query weather data via the weather MCP server. Use when you need current weather, forecasts, or climate data.
assign_when: Worker needs weather information for a task
---

# Weather Operations

## Overview

Use this skill to query weather data via the centralized MCP Server.

## get_weather

Get current weather for a city:

\```bash
mcporter call mcp-weather.get_weather city=Tokyo units=metric
\```

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| city | string | yes | City name |
| units | string | no | Temperature units (default: metric) |

Step 4: Confirm to your coordinator

After generating the skill, reply to your coordinator confirming:

  • You pulled the updated config
  • You discovered N tools on the new server
  • You generated a skill at ~/skills/<name>-operations/SKILL.md
  • You're ready to use the new tools

Important Notes

  • Not installed? If mcporter command is not found, install it: npm install -g mcporter
  • Transport: MCP Servers use HTTP transport (configured in config/mcporter.json)
  • Auth: Authorization header with Bearer token is auto-configured — you don't need to manage credentials
  • Permissions: Your MCP access is controlled by your coordinator. If you get 403 from the MCP Server, ask your coordinator to re-authorize your access
  • Config not found: If ./config/mcporter.json doesn't exist yet, use your file-sharing skill first; your coordinator publishes the config after setting up MCP servers

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Find worker agents in Nacos that match a task, recommend candidates, and import the administrator's chosen worker. It also supports importing a specified nacos package URI, with worker name confirmation and direct reporting of installation failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Find a suitable worker for an unassigned task
  • Compare Nacos worker candidates before importing
  • Import a worker from a specified nacos package URI
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

Prepare an existing OpenClaw setup for import as an AgentTeams managed Worker. Analyze tool dependencies, adapt role instructions and scheduled jobs, and build a ZIP package containing the configuration and custom image requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Moving standalone OpenClaw into AgentTeams
  • Reviewing required tool dependencies
  • Adapting role instructions for a Worker
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

Manage communication channels by identifying senders, maintaining trusted contacts, and setting the administrator's primary notification destination. It also covers first contact on a new channel and contacting the administrator across channels, with rules for handling unknown senders.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Identify who sent a message in a room
  • Add or remove trusted contacts
  • Configure the administrator's primary notification channel
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

Prepare coding tasks for delegation to an authorized agent’s AI command-line tool. Set up and synchronize the workspace, write precise change requests, then review returned changes and run relevant checks before reporting completion.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Delegating code implementation or bug fixes to an AI CLI
  • Writing coding requests with clear acceptance criteria
  • Reviewing and testing changes returned by a CLI
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

Run AI coding command-line tools on behalf of worker agents using their prepared prompts and workspaces. Detect available tools, configure delegation, return results, and apply supported execution controls such as time budgets and permission settings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Running coding tools for worker agents
  • Detecting and selecting available coding CLIs
  • Setting Qwen Code permissions and time budgets
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

Guide agent replies in Matrix chat rooms, including when to mention a coordinator, report completion, raise blockers, or answer questions. The rules limit repetitive acknowledgments and stop exchanges that add no new task, question, or decision.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Reporting task completion to a coordinator
  • Raising blockers or questions that need action
  • Reducing repetitive acknowledgments
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

agentscope-ai의 스킬 모두 보기

이 스킬의 문제 신고