Microsoft 365 Copilot + Jira: What the Integration Can (and Can't) Do in 2026
Partly — Microsoft ships an official Jira Cloud Copilot connector, but it’s read-only. It crawls your Jira Cloud issues and indexes them into Microsoft Graph so Copilot, Copilot Search, and Microsoft Search can ground answers in your project data — “summarize CP-1234,” “show high-priority bugs from the last seven days.” It does not write back: through the connector, Copilot can’t create an issue, add a comment, or transition a ticket. Writing to Jira exists on a different path — Atlassian’s own Jira Cloud plugin for Copilot in Microsoft Teams, which can search, create, update, and comment on issues from a Teams chat. And either way, everything happens inside a Copilot session you’re driving — nothing watches your board between prompts.
Here’s what each path actually does, how to turn them on, where the ceiling is, and what to use if you want Jira-adjacent work that runs on its own.
What Microsoft 365 Copilot can actually do with Jira
Through the Jira Cloud connector (the official Microsoft path, read-only):
- Answer questions grounded in issue data. “Give me the details of issue DESK-101, including priority and assignee,” “summarize the status of project Alpha based on Jira issues,” “what are the blockers for the API migration task?” — answered from indexed Jira data, without leaving Teams or Outlook.
- Search Jira issues across Microsoft 365. Indexed issues show up in Copilot, Copilot Search, and Microsoft Search, with semantic search over title, description, status, project, dates, assignee, and priority. Custom fields can be indexed too.
- Respect Jira permissions. In Only people with access to this data source mode, the connector maps Jira user emails to Microsoft Entra ID and honors Jira’s Browse-projects and issue-level security, so a user only sees issues they can already see in Jira.
- Ground custom agents. Developers can use the connector as a knowledge source in declarative agents built in Copilot Studio, Copilot Studio agent builder, or the Microsoft 365 Agents Toolkit — still for retrieval, not writing.
Through Atlassian’s Jira Cloud plugin for Copilot in Microsoft Teams (the write path, in a Teams chat):
- Create, update, and comment on issues from a plain-language prompt in Teams — “create a bug for the login timeout,” “add a comment to DESK-101,” “update the status.”
- Find and summarize tickets assigned to teammates or across a period, alongside the create/update actions.
For a fully custom write agent, teams can also wire Atlassian’s Remote MCP server into a Copilot Studio agent, exposing tools like searchJiraIssuesUsingJql and createJiraIssue. That’s a build-it-yourself route, not a turnkey feature.
How to set it up
The read-only connector is a tenant-admin job:
- In the Microsoft 365 admin center, go to Copilot → Connectors, select Atlassian Jira Cloud, and follow the deployment guide.
- Set up the Jira Cloud service account and grant Browse projects (mandatory for crawling), plus Browse users and groups if you want security trimming, per the Jira Cloud service setup.
- Configure the crawl schema — title, description, status, assignee, priority, and any custom fields — set the access model (Everyone or Only people with access to this data source), and let the crawl run. It supports incremental and full crawls for freshness.
- Test in Copilot with something read-only: “Summarize the open high-priority issues in the support project.”
To write to Jira, install Atlassian’s Jira Cloud plugin for Copilot in Teams: you need a Microsoft 365 Copilot license, extensions enabled in your tenant, and an Atlassian account. Add Copilot for Microsoft 365 in Teams, enable the Jira Cloud plugin, and authenticate with Atlassian. It’s a separate plugin from the Graph connector, and it acts only when a person prompts it.
The limits that matter
- The connector is read-only. It indexes issues for grounding and search — it can’t create, comment on, or transition anything back in Jira. Microsoft’s own docs describe it as surfacing and searching issues, full stop.
- Cloud only, and no attachments. The connector supports Jira Cloud-hosted instances only — Jira Server and Jira Data Center need the separate Jira Data Center connector — and attachments aren’t indexed, so Copilot can’t reason over files on a ticket.
- Writing means a second product and a live chat. Atlassian’s Teams plugin can create and update issues, but it requires a Microsoft 365 Copilot license, lives inside Teams, and every action is a person typing a prompt in a session.
- No triggers, ever. Neither path fires on a Jira event. Copilot answers when you prompt it; the plugin creates an issue when a person asks. A bug can sit unassigned or a blocker can breach its SLA over the weekend and nothing moves on its own.
- Session-bound and tenant-scoped. Every action needs a driver in a live session, and access is bounded by your tenant’s licensing and each user’s Jira permissions. There’s no standing watch on your board.
If you want Jira-adjacent work that runs on its own: Carly
The moment you want something to happen around Jira without you in the chat — a new bug triaged and routed within minutes, a nudge when an issue sits in “In Review” too long, a Monday sprint digest built and emailed, a blocker posted to the right Slack channel the moment it’s flagged — you’ve crossed past what a grounding connector or a manual Teams plugin is for.
That’s where Carly fits. Carly is an AI executive assistant built to act on triggers, not just answer in a session:
- Fires on events and schedules, 24/7, in the cloud. When an issue is created, changes status, or goes stale in Jira, Carly reacts — summarizes it, emails the owner, transitions or updates the ticket, posts to Slack — while your laptop is closed.
- Actually reads and writes. Jira is a native Carly integration, so Carly can create issues, add comments, transition tickets, and update fields — not just surface them in a chat.
- Sends, not just drafts. Carly drafts and sends email across Gmail and Outlook, books meetings, manages tasks, and records meetings — the follow-through that stops at the chat with Copilot.
- Builds the workflow by interviewing you. Tell Carly “when a bug is filed as high priority, assign it to the on-call engineer and email me a recap” in plain English; it interviews you and builds it — no admin center, no crawl schema, no prompt engineering.
Carly connects to 200+ tools across 40+ categories natively, plus any other tool via your own API key — paste it on carlyassistant.com/integrations. AI agents start at $35/month, and steps in a workflow that don’t use AI run free and unlimited. See integrations.
Microsoft 365 Copilot vs Carly
| Microsoft 365 Copilot (Jira) | Carly | |
|---|---|---|
| Answer questions grounded in Jira data | Yes (connector, read-only) | Yes |
| Search Jira issues in Microsoft 365 | Yes | Via the integration |
| Create / update issues in Jira | Only via Teams plugin (extra license) | Yes, natively |
| Comment on and transition issues | Via Teams plugin, by hand | Yes |
| Data reachable | Issues + metadata, no attachments | Full API scope |
| Acts on Jira triggers / events | No | Yes |
| Monday sprint digest, on schedule | No | Yes |
| Sends email as part of the flow | No | Yes (Gmail + Outlook) |
| Works while laptop is closed | No (session-bound) | Yes (cloud, 24/7) |
| Setup | Admin center + connector (+ Teams plugin for writes) | Describe it in plain English |
| Pricing | Microsoft 365 Copilot license per user | AI agents from $35/mo |
Copilot’s Jira connector is a grounding layer that pulls issue context into your chats. Carly is a teammate that acts on Jira events as they land.
Frequently Asked Questions
Does Microsoft 365 Copilot work with Jira?
Yes, for reading. Microsoft ships an official Jira Cloud Copilot connector that indexes Jira Cloud issues and their metadata into Microsoft Graph so Copilot and Microsoft Search can answer questions grounded in your project data. It’s read-only — it surfaces and searches issues but doesn’t write anything back to Jira.
Can Microsoft 365 Copilot create or update issues in Jira?
Not through the connector. Writing exists on a separate path: Atlassian’s Jira Cloud plugin for Copilot in Microsoft Teams can search, create, update, and comment on issues from a Teams chat, and a custom Copilot Studio agent can call Atlassian’s Remote MCP server for actions like createJiraIssue. Both require a Microsoft 365 Copilot license, and every action is a person prompting in a live session.
How do I connect Copilot to Jira?
A tenant admin adds the connector in the Microsoft 365 admin center → Copilot → Connectors → Atlassian Jira Cloud, sets up the Jira service account with Browse-projects permission, configures the crawl schema and access model, and runs a crawl. See Microsoft’s deployment guide. Note it supports Jira Cloud only — Server and Data Center use a separate connector.
Can Copilot react to a new Jira issue or a stalled ticket automatically?
No. Neither the connector nor the Teams plugin fires on Jira events — Copilot answers when you prompt it, and the plugin creates or updates an issue when someone asks. For “when a bug is filed, triage and route it” or “when an issue stalls, nudge the owner,” you need a trigger-based assistant like Carly, which integrates natively with Jira and runs in the cloud around the clock.
More: Best AI project management tools · Best AI tools for project managers · Claude + Jira · ChatGPT + Jira
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
