Connect Confluence with Unblocked to give AI agents your team’s docs

Confluence often contains the durable explanation that code and tickets omit: architecture decisions, operating procedures, RFCs, and team conventions. Unblocked treats the selected spaces as evidence that can confirm or qualify what an agent finds in the repository.

Confluence context is reconciled with your code, pull requests, tickets, and chat, so an agent answering a question can pull the design doc that explains why the code works the way it does — not just the code itself.

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

• Pages and blog posts — Unblocked indexes the pages and blog posts from the spaces you grant access to, including rendered macro content, and cites the page it used.
• Space-level scoping — Grant access to all spaces for the best coverage, or restrict to a subset depending on your team’s needs.
• Identity sync with an admin install — A Confluence admin install lets Unblocked sync identities, so Data Shield can enforce per-user permissions without each user connecting manually.
• Cross-source synthesis — Confluence docs are combined with your code, pull requests, Jira tickets, and Slack threads into a single knowledge graph.

Need screenshots or troubleshooting?This is a concise connection summary. Follow the complete setup guide ↗

Prerequisites

• An Unblocked account (free to start).
• A Confluence account. A Confluence admin is recommended — required to install the Unblocked for Confluence app and to sync identities when Data Shield is enabled. Confluence Data Center connects with a Personal Access Token instead of the app install.
• An MCP-compatible coding agent (Claude Code, Cursor, Windsurf, etc.) to use the context in your editor.

Step 1: Connect Confluence to Unblocked

1. In Unblocked, go to Settings → Data Sources, click Connect Another, and under Documentation select Confluence.
2. Authorize your Confluence account with Unblocked. On Confluence Data Center, paste a Personal Access Token instead of authorizing via OAuth.
3. If you are a Confluence admin, install the Unblocked for Confluence app, then click Verify Installation. (Data Center does not use the app install.)
4. Select the spaces to index (all, or a subset) and click Save Settings.

Step 2: Install the Unblocked MCP server

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

The install script supports macOS only. On Windows or Linux, add the server manually using the configuration below, or follow the manual install guide ↗.

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

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

https://getunblocked.com/api/mcpsse

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

Unblocked acts as the MCP context layer for your Confluence data, searching pages, blog posts, spaces alongside your other connected sources and returning cited results through these tools:

• context_researchMulti-source research across your Confluence pages and blog posts, plus your code, pull requests, and other connected sources. Returns a synthesized answer with citations back to the Confluence page it used.
• context_get_urlsFetches the full content behind a Confluence page URL your agent encounters — plus GitHub, Jira, Linear, Notion, Slack, and more.

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

• What is our architecture for the billing service, per the design docs?
• Where is the runbook for handling a failed deploy?
• What did the RFC decide about API versioning?
• Which Confluence page documents our on-call process?