MCP Tools

Introduction

MCP Tools are core components of the Model Context Protocol (MCP), designed to enable AI agents to call external functions or services through standardized interfaces.

• Function Exposure: Encapsulate external services or functions as tools, allowing AI agents to call them through standardized interfaces.

• Context Sharing: Allow Agents to carry context information when calling tools, enabling more intelligent interactions.

• Task Collaboration: Support the combination of multiple tools to help AI agents complete complex tasks.

Creation

First, select the Tool panel. Here, you can choose either Create From Blank or Create From Template. In this example, we’ll go with the first option — Create From Blank.

After clicking Create, you will be redirected to the Tool Creation Panel, where you need to configure the following information:

• Avatar The icon or image representing your tool. This helps visually identify the tool in the interface.

• Name The internal name of the tool. Tool name can only contain letters, numbers, and underscores (e.g., my_custom_tool). This name is used programmatically and must follow naming rules.

• Display Name The name shown to users, such as when the tool is used by an agent. There are no restrictions on characters, so you can use spaces, symbols, or non-English characters if needed (e.g., My Custom Tool).

• Description A brief explanation of what the tool does. This helps others (and yourself) understand the purpose of the tool at a glance.

• Create Tool Type Choose the type of tool to create.

MCP API Schema

The following example illustrates the standard JSON format used in the MCP API Schema to configure the Server-Sent Events (SSE) endpoint for event push notifications:

{
  "server_name": {
    "url": "https://actions.zapier.com/mcp/{sample}/sse"
  }
}

• server_name represents the identifier for the MCP service, typically used to distinguish different service nodes or functional modules.

• url specifies the SSE endpoint URL through which clients establish a connection to receive real-time event streams from the MCP platform, such as agent status updates or flow execution feedback.