How to Use the Sally MCP in Mastra AI

Q: What happens if a frontline worker goes offline?

The built-in workflow engine caches the updatetask payload. It applies exponential backoff until the connection restores. No data drops just because someone walked into a dead zone.

Build resilient frontline workflows with Mastra AI and the Sally MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sally MCP to Mastra AI

Create your Vinkius account to connect Sally to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sally with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Auto-Retry Task Dispatch

Firing `create_task` assigns a job to a deskless worker through the Mastra AI workflow engine. If the network drops on the factory floor, the framework automatically retries with exponential backoff. You configure the agent to keep trying until the system confirms receipt. Priority levels from P1 to P4 get set based on conditional logic you define. Changing a job's state requires the `update_task` tool. Your workflow can catch a failure, switch the status, and alert a manager. The entire sequence happens without a human touching a keyboard.

Conditional Shift Audits

Triggering `get_timesheet_report` pulls the labor data into your Mastra AI pipeline. The agent evaluates the hours against your predefined budget thresholds. When a project runs over, the workflow branches to notify operations. You match those hours against active jobs using `list_projects`. The framework cross-references the workspace data and flags discrepancies. Deploying this logic takes one command, pushing your audit system to any cloud provider.

Sally MCP Server Chat Routing

Invoking `get_board` reads the current state of your frontline Kanban setup. Mastra AI parses the columns to see where bottlenecks exist. As a column fills up, the agent steps in to reallocate resources. The workflow then uses `add_comment` to tell the team why tasks moved. Workers see the update in their mobile app instantly. You can even set requireToolApproval if you want a shift lead to sign off before the message sends.

Setup guide

Set up Sally MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Sally tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "sally-mcp-client",
  servers: {
    "sally-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Sally Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Sally tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Sally transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Sally. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Sally now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Sally MCP in Mastra AI

Install @mastra/mcp@latest and set up a new MCPClient. Pass the URL into the servers object. The framework auto-detects if it should use Streamable HTTP or SSE.

You just enable requireToolApproval on the specific tool. If the agent tries to run create_project, the workflow pauses. A manager clicks approve, and the execution resumes.

Run mcpClient.listTools() and spread the result into your agent's tool array. The framework handles the type mapping automatically. Your agent immediately knows how to talk to deskless workers.

The built-in workflow engine caches the update_task payload. It applies exponential backoff until the connection restores. No data drops just because someone walked into a dead zone.

Clock-in records and shift durations pass through a zero-trust architecture. Mastra AI only holds the token in memory during the execution phase. Nobody can intercept the labor data because the connection requires explicit endpoint authentication.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript