> For the complete documentation index, see [llms.txt](https://aphid-ai.gitbook.io/aphid-ai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://aphid-ai.gitbook.io/aphid-ai-docs/aphid-api/integration-patterns/mcp-based-integration-model.md).

# MCP-Based Integration Model

Model Context Protocol provides a standardized way for AI agents to access external tools, data, and services. In an Aphid deployment, MCP can be used to wrap third-party systems and expose them as controlled, discoverable tools that agents can call.

* A third-party system exposes business functions as MCP tools, such as create\_ticket, search\_customer, update\_order, retrieve\_invoice, or schedule\_meeting.
* Aphid discovers available tools and uses tool descriptions, input schemas, permissions, and policies to decide when a tool is appropriate.
* The agent sends structured arguments to the MCP tool rather than free-form instructions.
* The MCP server returns structured results, errors, or next-step requirements.
* Aphid records the tool invocation, input summary, output summary, user context, and final action for auditability.

| MCP Component | Role in Aphid Architecture                                                                 |
| ------------- | ------------------------------------------------------------------------------------------ |
| MCP client    | The Aphid agent runtime that calls available tools.                                        |
| MCP server    | A connector service that exposes approved capabilities from a third-party system.          |
| Tool schema   | Defines tool name, purpose, input fields, output fields, and validation rules.             |
| Policy layer  | Determines whether the agent is allowed to call the tool and whether approval is required. |
| Audit layer   | Captures every tool call, result, error, and user-visible outcome.                         |


---

# 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, and the optional `goal` query parameter:

```
GET https://aphid-ai.gitbook.io/aphid-ai-docs/aphid-api/integration-patterns/mcp-based-integration-model.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.