Integration · Automate and collaborate

Jira y Confluence and Meteor AI agents

Connect Jira and Confluence to a Met: search, create and update issues, comment and read pages with Atlassian's official MCP.

Book a demo See every integration

How does Jira y Confluence connect to Meteor?

With the Jira and Confluence ready connector, your Met uses Atlassian's official MCP server with the permissions of the account the admin authorizes. In Jira it searches issues with JQL, gets one by its key, creates new issues, edits them, transitions them and adds comments. In Confluence it searches, reads, creates and updates content. It also runs semantic search across your Atlassian apps. The generic gateway to other writes and to deletions starts turned off.

What it automates

What a Meteor Met does with Jira y Confluence

Open an issue from a report

When a customer reports a problem on WhatsApp, the Met checks whether a similar issue already exists and, if not, creates a new one in the support project with what the customer said.

Answer how a case is going

If the customer asks about their case, the Met gets the issue by its key and replies with the current status and the team's latest comment.

Answer with the team's documentation

The Met searches Confluence for the page that explains a process or a policy and replies with what it says, with the link for anyone who wants to read it in full.

Leave the note in the right place

If the admin leaves writing on, the Met adds a comment to the issue or updates the Confluence page with what was agreed in the conversation.

21 tools

Everything your Met can ask Jira y Confluence for

Each one is a real action in the connector. You can switch off the ones you would rather it never used.

Tool	What it does
`atlassianuserinfo`	Returns the details of the Atlassian account that authorized the connection.
`getaccessibleatlassianresources`	Lists the Atlassian sites and apps the account can access, with their cloudId.
`search`	Runs semantic search across Jira, Confluence and connected apps, in natural language. In beta.
`getjiraissue`	Returns a Jira issue by its ID or key.
`searchjiraissuesusingjql`	Searches Jira issues with a JQL query.
`createjiraissue`	Creates a new Jira issue.
`editjiraissue`	Edits an existing issue, only on the fields that issue allows changing.
`transitionjiraissue`	Moves an issue to another status, or assigns it to a sprint or the backlog.
`addoreditjiraissuecomment`	Adds a comment to a Jira issue or edits an existing one.
`getconfluencecontent`	Reads Confluence content, such as pages, blogs, comments or databases.
`searchconfluence`	Searches Confluence content with a CQL query.
`createconfluencecontent`	Creates a page, a blog post, a whiteboard or other content in Confluence.
`updateconfluencecontent`	Updates Confluence docs, whiteboards or databases.
`getteamworkgraphcontext`	Returns the connected context of an Atlassian item, with its relationships to other items and apps.
`getteamworkgraphobject`	Returns all the data of one or several objects from their identifier or link.
`addteamworkgraphcontext`	Adds a relationship between two objects in the Teamwork Graph.
`getloomvideo`	Returns a Loom video's details and, if requested, its transcript, comments and action items.
`discover`	Searches in natural language for other tools in the Atlassian catalog that are not shown up front.
`executeread`	Runs a read tool from the catalog found with discover.
`executewrite`	Runs a write tool from the catalog found with discover. Starts turned off.
`executedestructive`	Runs a deletion tool from the catalog found with discover. Starts turned off.

The limits

What the Jira y Confluence integration does NOT do

We would rather say it here than have you find out during rollout.

It does not delete issues or comments by default. The gateway to deletion tools starts turned off in Met, and in Atlassian the Jira deletion group is disabled until an admin enables it.
It does not run deferred catalog writes unless you turn it on. The generic write tool starts turned off; creating and editing issues have their own tools.
It does not see more than the connected account. Everything follows that account's Atlassian permissions, and the organization admin decides which tool groups are allowed.
It does not ask you for confirmation in the chat before writing. The admin decides in Connections which actions stay on.
It does not pay your Atlassian plan. Usage runs on your account; Meteor does not resell the service.

Before you start

What you need to connect Jira y Confluence

1

An Atlassian account with Jira or Confluence

The account your team uses for Jira, Confluence or both. The Met works on the sites that account can access.
2

Connect it in Met

In Met, open Connections → Jira and Confluence → Connect. An Atlassian window opens so you sign in and authorize Met.
3

Tool groups allowed in Atlassian

Organization admins grant or revoke access by permission group, such as read, write or search. Jira deletion and project management come disabled.

Frequently asked questions

Questions about Jira y Confluence and Meteor

Because every tool needs the site's cloudId. Atlassian asks to look it up first, and the Met does so before searching or creating anything.

Yes, for reading: discover finds tools in the Atlassian catalog and executeread runs them. To write or delete that way, the admin has to turn on the generic gateways.

Yes. Semantic search covers Jira, Confluence and connected apps; there is also JQL search for Jira and CQL search for Confluence.

You do, with your Atlassian account and plan. Met does not charge for the actions your Met takes in Jira or Confluence.

Step by step