MCPorter Migration Tool
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md and install @zcwl/mcporter.
About this skill
What problem it solves
When an AI agent must call multiple protocol service endpoints or MCP-style connectors, manually tracking server addresses, transport types, credentials, and tool parameters is error-prone and hard to audit, especially when different connectors use different transports and credential schemes. This skill turns those operations into an executable CLI workflow, suitable for environments such as Claude Code or Cursor that support SKILL.md.
How it works
It wraps mcporter CLI operations:
- Service discovery: mcporter list shows registered connectors and exposed tools
- Configuration: mcporter config adds, updates, or removes connection settings
- Authentication: mcporter auth manages API keys, OAuth tokens, and bearer tokens
- Tool invocation: mcporter call sends parameters and returns structured results
- Health checks: mcporter ping reports reachability and latency
It supports stdio, SSE, and WebSocket transports for local processes, remote HTTP streams, and bidirectional realtime communication. Typical inputs include command, server, tool, and params; output follows assets/output.json.
Boundaries
This is a CLI-oriented skill. It does not develop or deploy the underlying protocol service, and it is not a GUI manager or a general-purpose API caller. If the environment requires a platform API key, configure it according to the dependency notes, but do not hard-code secrets into configuration files.
Use Cases
- Use `mcporter list` to verify registered MCP connectors and exposed tools before an integration test.
- Test a remote SSE connector by calling a tool with `mcporter call` and inspect the structured response.
- Manage dev, staging, and production connector settings with `mcporter config` while keeping credentials separated.
- Run `mcporter ping` across multiple connectors before release to check reachability and latency.
Best For
- AI agent integration engineers who need to manage connector addresses, transports, and authentication.
- MCP tooling engineers who want to list exposed tools, test calls, and inspect structured results.
- Platform engineers who need pre-release reachability and latency checks across connectors.
- Automation engineers migrating connector configurations and validating registered services.
Related Skills
A systematic code error fixing skill that follows a five-step workflow: Reproduce, Isolate, Understand, Fix, Verify, to help developers resolve code errors.
Supports inline SVG/HTML rendering and Mermaid code output, covering common technical diagram creation like architecture and flow diagrams.
Publish HTML, static assets, or build output as a public link, with account management, update, deletion, and AI safety review.
A comprehensive browser automation guide covering navigation, interaction, multi-tab management, and data collection, tailored for domestic web ecosystems and tools like Playwright/Selenium.