> 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/tools/mcp.md).

# mcp

[Model Context Protocol](https://modelcontextprotocol.io/) is a standard for exposing tools and data sources to AI systems. MCP servers can provide custom tools for databases, services, internal systems, local resources, and third-party APIs.

In Agent Forge, the MCP Tool block allows workflows to execute tools from MCP servers configured in workspace settings. This makes MCP a bridge between Agent Forge workflows and external tool ecosystems without requiring every tool to be built as a native Agent Forge integration.

### Usage Instructions

Configure an MCP server in workspace settings, then add the MCP Tool block to a workflow. Select the server, choose a tool exposed by that server, and fill in the dynamically generated arguments for that tool.

For a broader MCP setup guide, see the main [MCP documentation](file:///mcp).

### Configuration

| Parameter   | Type   | Required      | Description                                  |
| ----------- | ------ | ------------- | -------------------------------------------- |
| `server`    | string | Yes           | MCP server ID                                |
| `tool`      | string | Yes           | Tool name exposed by the selected MCP server |
| `arguments` | json   | Tool-specific | Arguments passed to the selected MCP tool    |

### Output

| Parameter | Type  | Description                                     |
| --------- | ----- | ----------------------------------------------- |
| `content` | array | Standard MCP content array returned by the tool |

### Notes

* Category: `tools`
* Type: `mcp`
* Available tools are resolved dynamically from the selected MCP server.


---

# 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/tools/mcp.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.