> For the complete documentation index, see [llms.txt](https://docs.otari.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.otari.ai/tools/add-an-mcp-server.md).

# Add an MCP server

MCP servers allow requests from a workspace to connect to external tools and services. Each server is configured at the **workspace level**, so you can control which MCP tools are available to requests within that workspace.

To add an MCP server:

1. Select the workspace in the top-left corner.
2. Go to **Tools** → **MCP servers**.
3. Click **Add MCP server**.
4. Enter a **Name** for the server. This must be unique within the workspace and is used to identify the server’s tools.
5. Enter the MCP server **URL**. The endpoint must be reachable from the Otari gateway.
6. If required, enter an **Authorization token**.
7. Optionally, add a **Purpose hint** describing when the model should use this server, for example, “Use for repository and issue lookups.”
8. Under **Allowed tools**, specify which tools from the MCP server the model can access. Enter the tool names separated by commas, or leave the field blank to make all tools offered by the server available.
9. Use **Enabled** to control whether the MCP server is available for requests. You can disable it without removing its configuration.
10. Click **Add MCP server** to save it.

Once added, the MCP server becomes available to requests in that workspace according to the configuration and allowed tools you defined.


---

# 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.otari.ai/tools/add-an-mcp-server.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.