📅 Book a 30-min Demo📞 Call/text (571) 293-0242
Connector · Work and issue tracking

Jira MCP Server & Agent Skill

Last updated

ibl.ai publishes a free Jira agent skill: a SKILL.md that teaches an AI agent to read and write Jira data and expose it as an MCP tool. Download it, connect your own Jira credentials, and run the agent on ibl.ai Agentic OS, where you own all the code and the data.

Jira Cloud holds projects, issues (work items) with their fields, comments, attachments, workflows and transitions, sprints and boards, and the users and permissions around them.

What is the Jira API, and what can an agent read from it?

Issues, projects, comments, workflows and transitions, users and fields. JQL search runs at /rest/api/3/search/jql (GET or POST) with nextPageToken paging; the old /rest/api/3/search was removed.

  • API: Jira Cloud platform REST API v3 (REST)
  • Access: Public, self-serve
  • Base URL: https://{your-domain}.atlassian.net/rest/api/3/
  • Authentication: Basic auth with email and API token; OAuth 2.0 authorization code (3LO)

Any Jira Cloud user can create an API token at id.atlassian.com. Apps register in the Atlassian developer console for OAuth 2.0 (3LO). Calls run with the user's own project permissions.

Basic auth base64-encodes email:api_token. OAuth 3LO authorizes at auth.atlassian.com; calls go to https://api.atlassian.com/ex/jira/{cloudid}/; offline_access returns rotating refresh tokens.

What can an agent read from Jira?

  • JQL search — GET or POST /rest/api/3/search/jql; page with nextPageToken. Use POST for long JQL.
  • Issues — Get an issue with its fields, status and assignee from the Issues group of the v3 API.
  • Transitions — GET /rest/api/3/issue/{issueIdOrKey}/transitions lists transitions the user can perform.
  • Comments — Read the comments on an issue.

What can an agent write to Jira?

  • Create issue — Create an issue in a project with summary, issue type and fields.
  • Transition issue — POST /rest/api/3/issue/{issueIdOrKey}/transitions; needs Browse projects and Transition issues permissions.
  • Edit issue or add comment — Update fields or add a comment to an issue.
  • Delete issue — Delete an issue; needs the delete permission in the project. Confirm with the user first.

Limits: Points-based hourly quota (65,000 points/hour global pool by default), burst limits (100 RPS GET/POST, 50 RPS PUT/DELETE per endpoint) and per-issue write limits. 429 with Retry-After and RateLimit-Reason headers.

Issues and comments hold internal business, engineering and customer data; service desk tickets may include personal data depending on the organization.

How do I connect Jira to an AI agent over MCP?

Atlassian publishes an official MCP server: Atlassian Rovo MCP Server.

Atlassian-hosted at https://mcp.atlassian.com/v2/mcp for Jira, Confluence and more. OAuth 2.1 or API token; respects user permissions; calls consume Rovo credits.

You can register that server on ibl.ai as it is, or use the SKILL.md below when you want the agent to call the Jira Cloud platform REST API v3 directly.

On ibl.ai an MCP connection is three records, and a working integration always needs all three:

  1. Register the server — POST …/mcp-servers/ with its URL, a transport (sse, websocket or streamable_http) and an auth_type of none, token or oauth2.
  2. Create a connection that holds the credential, scoped to the whole organization (platform), to a single agent, or to each user (user).
  3. Enable it on the agent — mcp-tool in tool_slugs and the server id in mcp_servers. Both lists are replaced, not merged, so read the settings first.

Jira supports per-user OAuth, so the server can use auth_type=oauth2 with auth_scope=user: each person connects their own Jira account in the chat the first time the agent needs it.

The field reference is in MCP server connections, and the /iblai-api-agent-mcp skill runs all three steps from a coding agent.

What does the Jira agent skill do?

The Jira skill is one SKILL.md file named iblai-connect-jira. It gives an agent the auth conventions, what to read, which writes need a person's confirmation, the ibl.ai MCP wiring, example prompts and guardrails.

Download the Jira SKILL.md

Save it as .claude/skills/iblai-connect-jira/SKILL.md, or in your agent's skills folder. The ibl.ai platform skills it calls come from one install:

$ npx skills add iblai/vibe --all

This connector skill is a starting point maintained on ibl.ai, not part of the iblai/vibe repository.

It was checked against Atlassian's documentation on October 20, 2026. Test it against your own Jira setup before you rely on it.

What can I ask a Jira agent to do?

  • “List all open bugs in the PAY project assigned to me, sorted by priority”
  • “Create a story in MOBILE for the login timeout fix and link it to PAY-142”
  • “Move PAY-210 to In Review and add a comment with the PR link”
  • “Summarize what the platform team completed in the last sprint”

How do I run a Jira agent on ibl.ai?

Agentic OS is where the agent runs on ibl.ai: it holds the Jira MCP connection, the model the agent uses, its instructions and its conversation history.

On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network.

Which ibl.ai agents work with Jira data?

Which ibl.ai platform skills does a Jira agent use?

What else should I know before connecting Jira to an AI agent?

Is there an official Jira MCP server?

Yes. Atlassian publishes Atlassian Rovo MCP Server.

You can register it on ibl.ai as an MCP server, or use the SKILL.md when you want the agent to call the Jira Cloud platform REST API v3 directly.

Who can get Jira API credentials?

Any Jira Cloud user can create an API token at id.atlassian.com. Apps register in the Atlassian developer console for OAuth 2.0 (3LO). Calls run with the user's own project permissions.

Does Jira data leave my infrastructure when an ibl.ai agent uses it?

On ibl.ai, you own all the code and the data. Self-hosted in your cloud or data center, the agent, its MCP connections and its conversation logs stay inside your perimeter.

Because the platform is model-agnostic, you can point the agent at a model you host, so Jira records need not reach a third-party model provider.

Is the Jira agent skill free to use?

Yes. The SKILL.md is a free download with no sign-up. It assumes you already have Jira credentials, and your agreement with Atlassian still governs how you use its API.

Which other data sources can an AI agent connect to alongside Jira?

Which other Enterprise systems have a connector?

Every connector, grouped by sector, is on the connectors hub.