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

# MCP servers

Connect your own tools and data sources to Zerve's agent with MCP servers.

MCP (Model Context Protocol) servers let you give Zerve's agent extra tools, such as access to an internal system, a data vendor's API or a research tool. When a server is connected, the agent can find and use its tools as it works.

Manage MCP servers in **Settings → MCP Servers**. Servers are connected per user, so the servers you add are available to your agent sessions.

## Adding a server

Each server has:

| Setting               | Details                                                            |
| --------------------- | ------------------------------------------------------------------ |
| **Name**              | What it's called                                                   |
| **URL**               | The server's address                                               |
| **Transport**         | How Zerve connects to it                                           |
| **Authentication**    | **OAuth**, a **static** credential such as an API key, or **none** |
| **Requires approval** | When on, the agent asks before using any of the server's tools     |

Credentials are stored in your organization's secure vault, not with the server's settings.

## Choosing which tools to allow

When you add a server, Zerve discovers the tools it offers. Each tool can be switched on or off individually, so you can allow only the ones you want the agent to use.

To pick up tools the server has added since, select refresh. Zerve rediscovers the tools and keeps your existing on and off choices.

You can also switch a whole server off without removing it.

## How the agent uses them

The agent doesn't load every tool from every server at once. Instead, it searches your connected servers for tools relevant to the task, and activates them as it needs them.

{% hint style="warning" %}
Tools from MCP servers can take actions in other systems. Turn on **Requires approval** for any server whose tools can change data or send anything outside Zerve.
{% 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.zerve.ai/zerve-docs/agents-in-the-workspace/mcp-servers.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.