> For the complete documentation index, see [llms.txt](https://docs.mozilla.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mozilla.ai/mcpd/requirements.md).

# Requirements

`mcpd` does not require every runtime on every machine. Install the `mcpd` binary, then install the runtime(s) needed by the MCP servers you plan to run.

## Runtime requirements

Use the package prefix in `.mcpd.toml` to tell which runtime a server needs:

| Package Prefix | Install           | Required When                                                                                             | URL                                                                 |
| -------------- | ----------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------- |
| `uvx::`        | `uv`              | At least one configured server package starts with `uvx::`                                                | <https://docs.astral.sh/uv/getting-started/installation/>           |
| `npx::`        | Node.js and `npx` | At least one configured server package starts with `npx::`, or you want to use `mcpd inspector`           | <https://docs.npmjs.com/downloading-and-installing-node-js-and-npm> |
| `docker::`     | Docker            | At least one configured server package starts with `docker::`, or you want to run `mcpd` itself in Docker | <https://www.docker.com/products/docker-desktop/>                   |

{% hint style="success" %}
**Quick start and tutorial**

The quick start and tutorial use the `time` server through `uvx`, so `uv` is required for those examples.
{% endhint %}

## Optional tools used in examples

| Tool   | Why You Might Want It                            | URL                   |
| ------ | ------------------------------------------------ | --------------------- |
| `curl` | Calling the `mcpd` HTTP API from the shell       | <https://curl.se/>    |
| `jq`   | Pretty-printing JSON responses in shell examples | <https://jqlang.org/> |

## Development-only requirements

| Tool           | Purpose                                                             | URL                                                       |
| -------------- | ------------------------------------------------------------------- | --------------------------------------------------------- |
| `Go >= 1.26.0` | Building `mcpd`, running tests, and contributing to the Go codebase | <https://go.dev/doc/install>                              |
| `uv`           | Building the GitBook docs site via `make docs`                      | <https://docs.astral.sh/uv/getting-started/installation/> |

{% hint style="info" %}
**Internet Connectivity**

`mcpd` typically needs internet access to resolve packages from remote registries and to download server dependencies on first run.
{% endhint %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.mozilla.ai/mcpd/requirements.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.