# Mcporter

> CLI access to MCP servers without loading them into agent context (saves tokens). Use when: (1) calling MCP tools on-demand, (2) want to avoid MCP context overhead.

- **Type:** Skill
- **Install:** `agentstack add skill-minghinmatthewlam-agent-guards-mcporter`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [minghinmatthewlam](https://agentstack.voostack.com/s/minghinmatthewlam)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [minghinmatthewlam](https://github.com/minghinmatthewlam)
- **Source:** https://github.com/minghinmatthewlam/agent-guards/tree/main/skills/mcporter

## Install

```sh
agentstack add skill-minghinmatthewlam-agent-guards-mcporter
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# MCPorter

Call MCP server tools via CLI without a persistent connection. Keeps tool schemas out of context.

## Quick Start

```bash
mcporter list                          # available servers
mcporter list  --schema        # tools + args (always run before first call)
mcporter call . key:val  # call a tool
```

## Rules

- Always run `mcporter list  --schema` before first call — tool names drift between versions.
- If a server is offline or auth-gated, report it and continue with fallback tools.

## Non-Obvious Workflows

### Chrome live-session debugging

Connects to the user's running Chrome with existing login state and cookies. Requires Chrome remote debugging and user consent prompt approval.

```bash
mcporter list chrome-devtools --schema
mcporter call chrome-devtools.list_pages
mcporter call chrome-devtools.select_page pageIndex:0
mcporter call chrome-devtools.take_screenshot
mcporter call chrome-devtools.evaluate_script function:"() => document.title"
```

### When to use mcporter vs direct MCP

- **mcporter**: One-off or infrequent tool calls. Keeps context clean.
- **Direct MCP**: Frequent use in a session, need streaming, tight integration.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [minghinmatthewlam](https://github.com/minghinmatthewlam)
- **Source:** [minghinmatthewlam/agent-guards](https://github.com/minghinmatthewlam/agent-guards)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-minghinmatthewlam-agent-guards-mcporter
- Seller: https://agentstack.voostack.com/s/minghinmatthewlam
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.