Jira MCP integration for AI agents | Unblocked

Jira integration details

Category

Issue trackers

Indexed data

issues, projects, sprints

Supported products

Jira Cloud · Jira Data Center

Works with

Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, OpenCode, VS Code — via one MCP server connection

Content reviewed

July 20, 2026

What the Jira integration adds

Jira issues capture requirements, implementation constraints, status changes, and discussion around planned work. Unblocked connects that delivery record to the resulting code and pull requests, helping an agent distinguish the original request from the decision that ultimately shipped.

Jira context is reconciled with your code, pull requests, and docs, so an agent can trace a feature or bug from the ticket that requested it to the code that shipped it — with the reasoning in between.

Once connected, any MCP-compatible coding agent — Claude Code, Cursor, Windsurf, GitHub Copilot, Codex — can pull this context through a single Unblocked MCP server connection.

What you get

• Issues and projects as context — Unblocked indexes the issues, projects, and discussions from the projects you select and cites the issue it used.
• Ticket-to-code tracing — Jira issues are linked to the pull requests and code that address them, so agents can follow a feature or bug end to end.
• Identity sync with an admin install — A Jira admin install lets Unblocked sync identities, so Data Shield can enforce per-user permissions without each user connecting manually.
• Cross-source synthesis — Jira issues are combined with your code, pull requests, Confluence docs, and Slack threads into a single knowledge graph.

How to connect Jira to Unblocked

Prerequisites

• An Unblocked account (free to start).
• A Jira account. A Jira admin is recommended — required to install the Unblocked for Jira app and to sync identities when Data Shield is enabled.
• An MCP-compatible coding agent (Claude Code, Cursor, Windsurf, etc.) to use the context in your editor.

Step 1: Connect Jira to Unblocked

1. In Unblocked, go to Settings → Data Sources, click Connect Another, and under Issues select Jira.
2. Authorize your Jira account with Unblocked.
3. If you are a Jira admin, install the Unblocked for Jira app, then click Verify Installation.
4. Select the projects to index (all, or a subset) and click Save Settings.

Step 2: Install the Unblocked MCP server

On macOS or Linux, one command auto-detects and configures your supported agents (Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, OpenCode, VS Code):

curl -fsSL https://getunblocked.com/install-mcp.sh | bash

On Windows, or when you prefer remote MCP, add the server manually using the configuration below, or follow the manual install guide.

Claude Code

Add the remote server, then run /mcp in Claude Code, select unblocked, and log in via OAuth:

claude mcp add -s user --transport http unblocked https://getunblocked.com/api/mcpsse

Cursor

Open View: Open MCP Settings → Add Custom MCP, add the server, then click Connect to authenticate via OAuth:

{
  "mcpServers": {
    "unblocked": {
      "url": "https://getunblocked.com/api/mcpsse"
    }
  }
}

Other MCP clients

Any MCP-compatible client (Windsurf, Codex, VS Code, Claude Desktop, and others) can connect to the remote server with OAuth:

https://getunblocked.com/api/mcpsse

Connect Jira to Claude Code, Cursor, and other AI agents

To give Claude Code, Cursor, GitHub Copilot, Codex, or another MCP-compatible AI coding agent access to Jira context, connect Jira to Unblocked and add the single Unblocked MCP server to your agent.

Unblocked acts as the MCP context layer for your Jira data, searching issues, projects, sprints alongside your other connected sources and returning cited results through these tools:

• context_research Multi-source research across your Jira projects and issues, plus your code, pull requests, and other connected sources. Returns a synthesized answer with citations back to the Jira issue it used.
• context_get_urls Fetches the full content behind a Jira issue URL your agent encounters — plus GitHub, Linear, Confluence, Notion, Slack, and more.
• research_task Investigates a broader question across your Jira issues, code, pull requests, docs, and Slack together, synthesizing a research brief instead of a single citation — useful when you don’t know which ticket to start from.

Questions to ask an AI agent about Jira

Questions you (or your agent) can ask Unblocked about your Jira data:

• Which tickets are linked to the payment-refactor work?
• What are the acceptance criteria for PROJ-123?
• What was the reasoning behind closing the caching epic?
• Which open issues are blocking the next release?