> For the complete documentation index, see [llms.txt](https://whitepaper.aitech.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://whitepaper.aitech.io/agentforge/blocks/mcp_input.md).

# mcp\_input

The MCP Input block turns a workflow into a callable MCP tool when the workflow is deployed through MCP. It defines the tool name, tool description, and input schema that MCP clients see.

{% hint style="info" %}
MCP Input is for workflows that should be exposed as tools to MCP clients. Use the MCP Tool block when a workflow needs to call tools from an external MCP server.
{% endhint %}

### Overview

The MCP Input block acts as the entry point for MCP tool execution:

* **Tool Name** - The name exposed to MCP clients
* **Tool Description** - A plain-language explanation of what the tool does
* **Input Schema** - The structured argument schema expected from the MCP client

### Configuration Options

#### Tool Name

The callable tool name. Use a concise, action-oriented name such as `get-weather`, `lookup-customer`, or `summarize-ticket`.

#### Tool Description

Describe what the tool does and when an MCP client should call it. Good descriptions help agents choose the right tool.

#### Input Schema

Define the structured fields the MCP client can send. These values become the tool arguments passed into the workflow.

### How It Works

{% stepper %}
{% step %}
Add an MCP Input block to the workflow.
{% endstep %}

{% step %}
Define the tool name, description, and schema.
{% endstep %}

{% step %}
Connect the MCP Input block to downstream workflow logic.
{% endstep %}

{% step %}
Deploy the workflow as MCP so clients can call it as a tool.
{% endstep %}
{% endstepper %}

### Inputs and Outputs

#### Input

| Parameter | Type | Description                        |
| --------- | ---- | ---------------------------------- |
| `input`   | json | Arguments passed by the MCP client |

#### Output

| Parameter  | Type | Description                                          |
| ---------- | ---- | ---------------------------------------------------- |
| `response` | json | Tool arguments passed downstream to connected blocks |

### Notes

* Category: `blocks`
* Type: `mcp_input`


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://whitepaper.aitech.io/agentforge/blocks/mcp_input.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.