Asana MCP integration for AI agents | Unblocked

Asana integration details

Category

Issue trackers

Indexed data

projects, tasks, comments

Supported products

Asana

Works with

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

Content reviewed

July 20, 2026

What the Asana integration adds

Asana records the cross-functional plan around engineering work, including task ownership, project updates, requirements, and follow-up discussion. Unblocked makes selected projects usable as cited context when an agent needs the business or delivery reasoning behind a code change.

Asana context is reconciled with your code, pull requests, and docs, so an agent can connect the task that requested a change to the code and discussion behind it.

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

• Projects, tasks, and comments — Unblocked indexes the projects, tasks, and comments from your selected workspace and cites the task it used, with its project name attached.
• Private project linking — Team members can add their own private projects by linking their Asana account, so relevant work is included without over-sharing.
• Workspace and project scoping — Choose a workspace and the specific projects to index to match how your team plans its work.
• Cross-source synthesis — Asana tasks are combined with your code, pull requests, docs, and Slack threads into a single knowledge graph.

How to connect Asana to Unblocked

Prerequisites

• An Unblocked account (free to start).
• An Asana account with access to the workspace and projects you want to index.
• An MCP-compatible coding agent (Claude Code, Cursor, Windsurf, etc.) to use the context in your editor.

Step 1: Connect Asana to Unblocked

1. In Unblocked, go to Settings → Data Sources → Connect another data source, and under Project management select Asana.
2. Sign in to Asana and grant access to Unblocked.
3. Select the workspace to index, then choose the projects.
4. Click Save Settings — Unblocked begins referencing those projects in its answers.

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 Asana 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 Asana context, connect Asana to Unblocked and add the single Unblocked MCP server to your agent.

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

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

Questions to ask an AI agent about Asana

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

• Which Asana task requested the new export feature?
• What is the status of the tasks in the current sprint project?
• What did the comments on this task decide about scope?
• Which tasks are assigned for the upcoming release?