> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/umbraco-in-ai/17.latest/mcp/base-mcp/sdk.md).

# MCP Server SDK

The `@umbraco-cms/mcp-server-sdk` package provides infrastructure for building Model Context Protocol (MCP) servers that expose Umbraco APIs to AI assistants. The SDK handles tool registration, API communication, error handling, configuration loading, tool filtering, and MCP chaining.

## Getting Started

Create a new MCP server project with the [Create Umbraco MCP Server](/umbraco-in-ai/17.latest/mcp/base-mcp/create-umbraco-mcp-server.md) CLI. The project template includes this SDK and configures it for you.

## Documentation

| Guide                                                                               | Description                                                  |
| ----------------------------------------------------------------------------------- | ------------------------------------------------------------ |
| [Tool Authoring](/umbraco-in-ai/17.latest/mcp/base-mcp/sdk/tool-authoring.md)       | How the system works, adding collections and tools, examples |
| [API Helpers](/umbraco-in-ai/17.latest/mcp/base-mcp/sdk/api-helpers.md)             | API call helpers, HTTP client, ProblemDetails handling       |
| [Tool Filtering](/umbraco-in-ai/17.latest/mcp/base-mcp/sdk/tool-filtering.md)       | Modes, slices, collections, configuration flow               |
| [MCP Chaining](/umbraco-in-ai/17.latest/mcp/base-mcp/sdk/mcp-chaining.md)           | Proxying, delegation, and composite tool patterns            |
| [Configuration](/umbraco-in-ai/17.latest/mcp/base-mcp/sdk/configuration.md)         | Server config, env vars, CLI flags, custom fields            |
| [Constants](/umbraco-in-ai/17.latest/mcp/base-mcp/sdk/constants.md)                 | Well-known Umbraco IDs reference                             |
| [Testing and Evals](/umbraco-in-ai/17.latest/mcp/base-mcp/sdk/testing.md)           | Unit testing, snapshot helpers, LLM eval framework           |
| [Coverage Tracking](/umbraco-in-ai/17.latest/mcp/base-mcp/sdk/coverage-tracking.md) | Count tools and catalog ignored endpoints                    |


---

# 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://docs.umbraco.com/umbraco-in-ai/17.latest/mcp/base-mcp/sdk.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.