MCP Integration FAQs

Question 1

Can I use multiple MCP servers in one plugin?

Accepted Answer

Yes, you can define multiple servers within your .mcp.json or plugin.json file to orchestrate complex workflows spanning different external services.

Question 2

How do I secure my MCP integration?

Accepted Answer

You should use environment variables for sensitive tokens, prefer HTTPS/WSS connections, and strictly pre-allow only necessary tools in your command frontmatter instead of using wildcards.

Question 3

What is the Model Context Protocol (MCP)?

Accepted Answer

MCP is an open standard that enables AI models like Claude to securely interact with external data sources, APIs, and local tools through a unified, structured interface.

Question 4

What is the difference between stdio and SSE servers?

Accepted Answer

Stdio servers run as local child processes and are ideal for local tools or custom scripts, while SSE (Server-Sent Events) is designed for connecting to hosted cloud services and handling remote web requests.

Question 5

How does Claude Code handle MCP authentication?

Accepted Answer

Claude Code automatically manages OAuth flows for SSE servers, prompting the user in a browser on first use. For other types, it supports token-based authentication via headers or environment variables.

MCP Integration

Key Features

Use Cases

MCP Integration

Key Features

Use Cases