OAUTH 2.0
PROJECT MANAGEMENT
AI-native project management tool for task and document management with deep AI integration.
from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient
client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="dartaimcp")
mcp = MultiServerMCPClient({
"dartaimcp": {
"url": "https://mcp.scalekit.com/dartaimcp",
"headers": {"Authorization": "Bearer " + token}
}
})
tools = await mcp.get_tools()import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";
const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "dartaimcp" });
const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/dartaimcp
// Pass: Authorization: Bearer + tokenimport Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";
const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "dartaimcp" });
const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/dartaimcp
// Pass: Authorization: Bearer + tokenfrom google.adk.agents import LlmAgent
from scalekit import ScalekitClient
client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="dartaimcp")
# Connect to MCP at https://mcp.scalekit.com/dartaimcp
# Pass: Authorization: Bearer + token
.svg)
// shared token
audit → bot_service_account
// scalekit
audit → user_abc ✓
Does the agent access Dart AI 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 Dart AI OAuth token 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 Dart AI?
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 Dart AI.
What happens when a user revokes Dart AI 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.
Which tasks and docs can the agent create or update?
Only in workspaces the authorizing user belongs to. Task comments, time tracking, and doc edits attribute to that user in Dart, keeping project history accurate.
.svg)
