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

# MCP Server

Automate Symphony Messaging tasks, notify teammates, and use Symphony Messaging chat as context in Claude, Gemini or any other MCP client.

### Overview and capabilities

Symphony's MCP server connects Symphony Messaging to MCP-compatible AI clients.

You can automate tasks and notify teammates directly from an AI assistant, or use Symphony Messaging conversations as context for prompts in any MCP-compatible AI assistant.

It gives AI clients a standard way to discover tools, inspect inputs, and run actions in Symphony Messaging, reducing custom integration work and making tool-driven workflows easier to build, test, and govern.

### Security, premissions and data governance

Symphony's MCP server is built on Symphony applications and on-behalf-of (OBO) permissions.

It follows the same security model as authenticated apps in Symphony Messaging. For context, see [Planning Your App](https://docs.developers.symphony.com/ext-apps/planning-your-app.md), [App Authentication](https://docs.developers.symphony.com/ext-apps/app-authentication.md), and [OBO Authentication](https://docs.developers.symphony.com/ext-apps/app-authentication/obo-authentication.md).

Each user gets a dedicated OBO session when they use the server.

This gives organizations strong control and traceability:

* Users never access more data than they can already access in Symphony Messaging.
* Room membership, history sharing, and information barriers are enforced by default.
* Actions such as room creation or message sending are recorded in audit trail and content export as actions performed by the MCP server on behalf of the user.

This ensures the assistant remains aligned with existing permission boundaries within Symphony Messaging, and provides Admins with an extra control layer through application permissions.

Admins can use app permissions as an overlay to restrict which MCP actions are available. For example, they can allow read-only workflows and block authoring actions such as sending messages or creating rooms.

### Service activation

Symphony's MCP server must be enabled before you can use it.

{% hint style="warning" %}
Symphony's MCP server is an add-on to Symphony Services. It is subject to additional charges.

Contact the [Symphony team](https://symphony.com/contact/) to enable the service in your environment before you can start using it.
{% endhint %}

Once the service is enabled, you can connect Symphony's MCP server to any MCP-compatible AI client, including Claude, ChatGPT, Mistral, and other AI agents that support MCP protocol.&#x20;

### Connect with Symphony's MCP

Symphony's MCP server is a remote server that you can start using immediately with zero deployment required. Connect your MCP client, complete the authorization flow, and start prompting.

The MCP server is exposed through your tenant-specific URL, for example *`https://xxx.symphony.com/mcp-server/{appId}/mcp`* , where `appId` corresponds to the Symphony Messaging app used by the MCP server.

Symphony's MCP Server implements secure authorization using OAuth 2.1.

A dedicated setup guide will soon be available for each MCP client. Don't hesitate to contact the Symphony's support team at *<support@symphony.com>* if you need help for your first setup.


---

# 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.developers.symphony.com/ai-studio/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.
