> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nofire.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Atlassian

> Connect Atlassian to NOFire AI for ticket triage, runbooks, and incident documentation

Connecting Atlassian to NOFire AI gives your investigations access to your Atlassian workspace — issues, pages, projects, and service components. During incidents, NOFire can search for relevant runbooks, triage tickets, and post findings back — closing the loop between investigation and documentation.

Authentication uses an Atlassian **API token**. OAuth 2.0 support is coming soon.

<Info>
  This integration connects via Atlassian's [MCP server](https://support.atlassian.com/atlassian-rovo-mcp-server/docs/getting-started-with-the-atlassian-remote-mcp-server/). NOFire communicates with Atlassian's hosted endpoint — no additional infrastructure needed.
</Info>

<Warning>
  API token authentication is **disabled by default** on Atlassian's MCP server. An organization admin must enable it first:

  1. Go to **Atlassian Administration**
  2. Select **Apps** → **AI settings** → **Rovo MCP server**
  3. In the **Authentication** section, turn **API token** on

  See [Atlassian's MCP server settings](https://support.atlassian.com/security-and-access-policies/docs/control-atlassian-rovo-mcp-server-settings/) for details on domain allowlists and IP restrictions.
</Warning>

## What this enables

* **Find runbooks**: search Confluence for documented procedures by alert name, service, or error pattern
* **Incident context**: pull past Jira incidents and postmortems to inform current investigations
* **Ticket triage**: assess and prioritize incoming Jira issues based on production signals
* **Add comments**: post root cause analysis, investigation summaries, or status updates to Jira tickets

## Step 1: Create an Atlassian API Token

<Accordion title="Generate an API token" defaultOpen>
  1. Go to [Atlassian API Tokens](https://id.atlassian.com/manage-profile/security/api-tokens)
  2. Click **Create API token**
  3. Name it `nofire` and click **Create**
  4. Copy the token — you'll need it in Step 2

  <Note>
    The API token inherits your Atlassian account permissions. Use an account with read access to the Jira projects and Confluence spaces NOFire should be able to query.
  </Note>
</Accordion>

## Step 2: Add Atlassian Connection in NOFire AI

<Accordion title="Configure the connection" defaultOpen>
  1. Go to the **Connections** tab in the NOFire AI dashboard at [my.nofire.ai](https://my.nofire.ai)

  2. Select **Atlassian (MCP)** from the list and click **Next**

  3. Enter:
     * **Connection name** (e.g., `engineering-jira`)
     * **MCP Server URL**: `https://mcp.atlassian.com/v1/sse`
     * **Auth Header**: `Authorization`
     * **Auth Value**: `Bearer <your-api-token>`

  4. Click **Save** to test the connection and establish the integration

  Once connected, NOFire AI can query your Jira projects and Confluence spaces during investigations and chat sessions.
</Accordion>

## Example queries

### Runbooks

```
@NOFire AI find the runbook for high memory alerts on the payment service
```

```
@NOFire AI what does our Confluence say about the checkout service recovery procedure?
```

### Ticket triage

```
@NOFire AI show me the latest P1 incidents in Jira — are any related to today's alerts?
```

```
@NOFire AI triage INCIDENT-456 — what's the likely root cause based on production signals?
```

### Investigation documentation

```
@NOFire AI add the root cause summary to INCIDENT-456
```

### Pattern analysis

```
@NOFire AI what incidents have we had on the cart service in the last 30 days?
```

```
@NOFire AI are there recurring patterns across our recent P1 tickets?
```