mcporter

mcporter is a skill for Claude Code, Codex from agentscope-ai/AgentTeams. It costs 47 tokens per session (881 once invoked), scanned A, original, Apache-2.0.

A command-line guide for finding and calling MCP servers, which are services that expose tools to coding agents. It explains how to list servers, inspect their inputs, and send simple or structured requests.

In plain words
What is it for?
Use it when new MCP tools become available or when an external API must be discovered and called through the mcporter command.
Why use it?
It removes the guesswork from discovering external tools and calling them with correctly shaped arguments.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

AgentTeams is a runtime platform where multiple AI agents collaborate in shared Matrix rooms under the coordination of a manager. It is for human-supervised or enterprise workflows that need visible, auditable cooperation among agents running on different runtimes, with shared files and centralized traffic management.

agentscope-ai/AgentTeams · 5,568 stars · on GitHub · aliyun.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/agentscope-ai/agentteams/mcporter
Any agent
npx skills add agentscope-ai/AgentTeams --skill mcporter
Clone the repo
git clone --depth 1 https://github.com/agentscope-ai/AgentTeams

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcporter

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentscope-ai/agentteams/mcporter.svg)](https://agentmods.dev/skills/agentscope-ai/agentteams/mcporter)
Your own site
<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/mcporter"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/mcporter.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 881 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00881
Opus 5 $0.00023 $0.00441
Sonnet 5 $0.00009 $0.00176
Haiku 4.5 $0.00005 $0.00088

Measured 7d ago against content hash 6063f9d9dbd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcporter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

manager/agent/copaw-worker-agent/skills/mcporter/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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) |

Read the full file on GitHub · 114 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 114 lines · 47 tokens per session scan A 6063f9d9dbd2

Subscribe to this mod's changes

mcporter is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,568 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 881 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

plan-ceo-review

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…

GCWing/BitFun · 143 tokens

ship

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is…

GCWing/BitFun · 105 tokens

design-review

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…

GCWing/BitFun · 125 tokens

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…

GCWing/BitFun · 116 tokens

pre-landing-review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…

GCWing/BitFun · 75 tokens

autoplan

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…

GCWing/BitFun · 152 tokens