# MCP in Workflows — Advanced Agent Workflows and Skills

Source: https://www.geekswithgeeks.com/en/agent-workflows/tools-mcp

> Connect an agent to external systems through the Model Context Protocol and manage the risks.

## A standard plug

The **Model Context Protocol (MCP)** is an open standard that lets an agent connect to tools and data through MCP servers: for example a database, an issue tracker or a browser. You write or install a server once and any MCP-capable client can use it.

## Registering a server

Claude Code can add a server from the command line. Prefer read-only servers or scoped credentials for data sources.

```bash
claude mcp add --transport http issues https://mcp.example.com/mcp
claude mcp list
```

## Only install servers you trust

An MCP server can run code and its tool results go into the model's context. A malicious or compromised server can return instructions hidden in data. Review servers as you would any dependency.

**Quiz:** What does MCP standardise?

- [x] How agents connect to external tools and data
- [ ] How to format Python code
- [ ] How to price API calls
- [ ] How to train models

*Answer:* How agents connect to external tools and data. It is a common interface so one server works with many clients.
