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

# Overview of the DevOps MCP Server

{% hint style="warning" %}

#### Beta

The DevOps MCP server is in beta. Some tools may not work as expected yet, and this documentation may not reflect the latest changes to the server.
{% endhint %}

## ![](https://1800549522-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FRpUu5iMlzMFAudyBvMOl%2Fuploads%2FG5ZbxX918xOHwbAwAJ4n%2FSummary2-Small-Icon.svg?alt=media\&token=da26a67f-ff7f-47b3-8669-06be960dc2d7) Overview

The DevOps MCP (Model Context Protocol) server connects AI assistants, such as ChatGPT and Claude, to DevOps. Once connected, you can ask the assistant in plain language to work with your DevOps data, for example, to list the branches in a Topology, look up a pull request, or check the results of a deployment. The assistant uses the DevOps MCP tools to read your DevOps data and, when you allow it, to make changes such as creating branches, committing components, and running pipelines.

Each user connects with their own Flosum user, so the assistant works in DevOps as the user who signed in. You need a Flosum user with at least **Read access** to **DevOps**.

## Getting Connected

Connecting an AI assistant to the DevOps MCP server has two parts. A SystemAdministrator creates the Connected App once for your tenant, and then each user connects their own AI assistant.

{% stepper %}
{% step %}

### Create a Connected App

A SystemAdministrator creates one Connected App in Global Settings, and every user connects through it. See the following article.

* [Creating a Connected App for MCP Access](/global-settings/security/connected-apps/creating-a-connected-app-for-mcp-access.md)
  {% endstep %}

{% step %}

### Connect an AI Assistant

Each user adds the DevOps MCP server to their AI assistant and signs in with their Flosum user. Each AI assistant also has its own callback URL, which a SystemAdministrator adds to the Connected App the first time that assistant is connected. See the article for your AI assistant.

* [Connecting ChatGPT to the DevOps MCP Server](/devops/mcp-server/connecting-chatgpt-to-the-devops-mcp-server.md)
* [Connecting Claude to the DevOps MCP Server](/devops/mcp-server/connecting-claude-to-the-devops-mcp-server.md)
  {% endstep %}
  {% endstepper %}

## Using the DevOps MCP Server

Once your AI assistant is connected, start a new chat and ask it to work with your DevOps data. The assistant chooses which DevOps MCP tools to use for each request. See the following article for a description of the DevOps MCP tools and how to use them.

* [Using DevOps MCP Tools](/devops/mcp-server/using-devops-mcp-tools.md)


---

# 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.flosum.com/devops/mcp-server/overview-of-the-devops-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.