Asana MCP | OAuth Asana connector for AI agents

Tools your project management agent reaches for on Asana, scoped per user.

CALL ANY TOOL

List tasks and projects, create and update tasks, add comments, and track due dates.

asana_attachment_delete

Delete attachment

Delete an attachment permanently.

Parameters

Name

Type

Required

Description

attachment_gid

string

Required

GID of the attachment to delete

asana_attachment_get

Get attachment

asana_me_get

Get me

asana_project_create

Create project

asana_project_delete

Delete project

asana_project_duplicate

Project Duplicate

asana_project_get

Get project

asana_project_tasks_list

List project tasks

asana_project_update

Update project

asana_projects_list

List projects

asana_section_add_task

Section Add Task

asana_section_create

Create section

asana_section_delete

Delete section

asana_section_get

Get section

asana_section_update

Update section

asana_sections_list

List sections

asana_story_create

Create story

asana_story_get

Get story

asana_subtask_create

Create subtask

asana_tag_create

Create tag

asana_tag_delete

Delete tag

asana_tag_get

Get tag

asana_tag_update

Update tag

asana_tags_list

List tags

asana_task_add_followers

Task Add Followers

asana_task_add_project

Task Add Project

asana_task_add_tag

Task Add Tag

asana_task_create

Create task

asana_task_delete

Delete task

asana_task_duplicate

Task Duplicate

For more tools, view docs.

Build your Agent

Drop the toolkit in, point it at the user, and your project management agent can use Asana from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["asana"], toolNames: ["asana_tasks_list", "asana_task_get", "asana_task_create"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["asana"], toolNames: ["asana_tasks_list", "asana_task_get", "asana_task_create"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["asana"], toolNames: ["asana_tasks_list", "asana_task_get", "asana_task_create"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/asana",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Asana.

Search & recall

Copy the prompt

Copied

List all tasks assigned to me this week.

Copy the prompt

Copied

Show me overdue tasks in [project name].

Copy the prompt

Copied

Find tasks with [tag] across all projects.

Copy the prompt

Copied

What sub-tasks does [task name] have?

Action & creation

Copy the prompt

Copied

Create a task in [project]: [name] due [date].

Copy the prompt

Copied

Assign task [name] to [person] and set due to [date].

Copy the prompt

Copied

Mark task [name] as complete.

Copy the prompt

Copied

Add a comment to [task]: [text].

Projects & reporting

Copy the prompt

Copied

List all active projects in [workspace].

Copy the prompt

Copied

How many tasks are open by status in [project]?

Copy the prompt

Copied

Show project completion progress for [project].

Copy the prompt

Copied

What tasks were closed in the last 7 days?

SEE HOW AUTH WORKS

Users authorize Asana once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Asana

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Asana

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Asana

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Asana

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other project management agents and MCP connectors. Working code, live demos, fork what fits.

ENGINEERING

DevOps assistant agent

Triage GitHub incidents, open Linear tickets, and notify the on-call channel in Slack with context already attached.

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Task updates lose team attribution

A shared Asana token looks fine in a demo. In production, every task update and project write logs as the integration. Task ownership breaks. Workspace attribution breaks. Scalekit resolves the actual user's token so every Asana action is attributed to the right person.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Asana today. Linear, Jira, ClickUp tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Asana as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Asana oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Asana?

Yes. Pass a tool name filter to listScopedTools so the project management agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Asana.

What happens when a user revokes Asana access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent work across multiple Asana workspaces?

Yes, one workspace at a time per connected account. The user authorizes each workspace separately. Cross-workspace access stays denied; project and task permissions inherit native Asana roles.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit