Grain Watch MCP Server for Mastra AI 12 tools — connect in under 2 minutes
Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect Grain Watch through Vinkius and Mastra agents discover all tools automatically. type-safe, streaming-ready, and deployable anywhere Node.js runs.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import { Agent } from "@mastra/core/agent";
import { createMCPClient } from "@mastra/mcp";
import { openai } from "@ai-sdk/openai";
async function main() {
// Your Vinkius token. get it at cloud.vinkius.com
const mcpClient = await createMCPClient({
servers: {
"grain-watch": {
url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
},
},
});
const tools = await mcpClient.getTools();
const agent = new Agent({
name: "Grain Watch Agent",
instructions:
"You help users interact with Grain Watch " +
"using 12 tools.",
model: openai("gpt-4o"),
tools,
});
const result = await agent.generate(
"What can I do with Grain Watch?"
);
console.log(result.text);
}
main();
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Grain Watch MCP Server
Connect your Grain Watch Silo Temperature Monitoring API to any AI agent and take full control of real-time temperature tracking, humidity monitoring, hot spot detection, and AI-powered spoilage risk assessment through natural conversation.
Mastra's agent abstraction provides a clean separation between LLM logic and Grain Watch tool infrastructure. Connect 12 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.
What you can do
- Silo Management — List and manage all temperature-monitored silos with grain types and sensor status
- Real-Time Temperature — Get current temperature readings from all sensors throughout the grain mass
- Humidity Monitoring — Track relative humidity levels for condensation risk assessment
- Temperature History — Analyze historical temperature trends to detect developing hot spots
- Humidity History — Monitor humidity patterns for moisture migration and condensation detection
- Sensor Mapping — View complete sensor layout with positions, depths, and zones
- Hot Spot Alerts — Receive automatic alerts when localized heating indicates potential spoilage
- Spoilage Risk — Get AI-powered risk assessments combining temperature, humidity, and grain type
- Alert Management — Monitor all active alerts for temperature, humidity, and sensor issues
- Sensor Health — Track sensor battery levels, communication status, and operational health
- Facility Overview — Get comprehensive facility-wide temperature summaries for executive reporting
The Grain Watch MCP Server exposes 12 tools through the Vinkius. Connect it to Mastra AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Grain Watch to Mastra AI via MCP
Follow these steps to integrate the Grain Watch MCP Server with Mastra AI.
Install dependencies
Run npm install @mastra/core @mastra/mcp @ai-sdk/openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.ts and run with npx tsx agent.ts
Explore tools
Mastra discovers 12 tools from Grain Watch via MCP
Why Use Mastra AI with the Grain Watch MCP Server
Mastra AI provides unique advantages when paired with Grain Watch through the Model Context Protocol.
Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add Grain Watch without touching business code
Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation
TypeScript-native: full type inference for every Grain Watch tool response with IDE autocomplete and compile-time checks
One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure
Grain Watch + Mastra AI Use Cases
Practical scenarios where Mastra AI combined with the Grain Watch MCP Server delivers measurable value.
Automated workflows: build multi-step agents that query Grain Watch, process results, and trigger downstream actions in a typed pipeline
SaaS integrations: embed Grain Watch as a first-class tool in your product's AI features with Mastra's clean agent API
Background jobs: schedule Mastra agents to query Grain Watch on a cron and store results in your database automatically
Multi-agent systems: create specialist agents that collaborate using Grain Watch tools alongside other MCP servers
Grain Watch MCP Tools for Mastra AI (12)
These 12 tools become available when you connect Grain Watch to Mastra AI via MCP:
get_alerts
Returns alert type, severity (critical, warning, info), affected silo, timestamp, and recommended actions. Essential for comprehensive operational monitoring, issue detection, and management response. AI agents should use this when users ask "show me all active alerts", "what warnings have been triggered for silo 3", or need alert data for operational monitoring. Optional silo_id filters alerts for a specific silo. Get all active alerts for temperature, humidity, and sensor issues
get_current_humidity
Returns relative humidity (%) values from multiple sensor positions. High humidity combined with temperature indicates condensation risk and potential spoilage conditions. Essential for moisture migration detection, condensation risk assessment, and grain quality preservation. AI agents should reference this when users ask "what is the humidity level in silo 3", "show me humidity readings for silo 5", or need current humidity data for storage condition assessment. Get current humidity readings from sensors in a grain silo
get_current_temperature
Returns temperature values (Celsius) from multiple sensor positions throughout the grain mass including top, middle, bottom, and center zones. Essential for real-time grain condition monitoring, hot spot detection, and spoilage prevention. AI agents should use this when users ask "what is the current temperature in silo 2", "show me all temperature readings for silo 4", or need immediate grain temperature data for storage management decisions. Get current temperature readings from all sensors in a grain silo
get_facility_overview
Essential for executive reporting, facility-wide condition assessment, and strategic storage management. AI agents should use this when users ask "give me an overview of all my silos", "what is the overall temperature status across the facility", or need facility-level summaries for management reporting. Get comprehensive overview of all monitored silos and their temperature status
get_hotspot_alerts
Returns alert severity (critical, warning), affected silo, sensor zone location, temperature differential, detection timestamp, and recommended actions. Hot spots are early indicators of grain quality issues that require immediate attention. Essential for proactive grain management, spoilage prevention, and quality preservation. AI agents should use this when users ask "are there any hot spots detected", "show hotspot alerts for silo 3", or need early warning indicators of grain spoilage. Optional silo_id filters alerts for a specific silo. Get active hot spot detection alerts for all silos or a specific silo
get_humidity_history
Humidity patterns over time help identify moisture migration, condensation events, and drying effectiveness. Returns time-series humidity data (%) with timestamps from multiple sensor positions. Essential for moisture migration analysis, condensation detection, and storage safety monitoring. AI agents should reference this when users ask "show me humidity trends for silo 1", "has humidity been stable in silo 2", or need historical humidity data for storage management. Get historical humidity readings to track moisture migration patterns
get_sensor_health
Returns sensor IDs, positions, communication status, last reading time, battery levels (for wireless sensors), and operational status (active, offline, fault, needs calibration). Essential for sensor network maintenance, data continuity assurance, and monitoring system reliability. AI agents should reference this when users ask "are all sensors working in silo 5", "which sensors have gone offline", or need sensor health data for system administration. Get health status of all temperature and humidity sensors in a silo
get_sensor_map
Returns sensor IDs, physical locations (top/middle/bottom, center/perimeter), installation depths, and current operational status. Essential for understanding temperature distribution across the grain mass, identifying which sensor corresponds to which physical location, and troubleshooting sensor issues. AI agents should use this when users ask "show me the sensor layout for silo 4", "where are the sensors positioned in silo 6", or need sensor positioning data for temperature analysis interpretation. Get the layout and positions of all temperature sensors in a silo
get_silo_details
Essential for understanding silo context before analyzing temperature data, planning aeration strategies, or generating storage condition reports. AI agents should reference this when users ask "tell me about silo 3", "what grain is stored in silo 5 and how many sensors does it have", or need detailed silo metadata for informed analysis. Get detailed information about a specific grain silo
get_silos
Returns silo IDs, names, locations, grain types, current temperature status, and monitoring health. Essential for facility overview, silo inventory management, and selecting specific silos for detailed temperature analysis. AI agents should use this when users ask "show me all my monitored silos", "list temperature-monitored storage units", or need to identify available silos before querying temperature readings or alerts. List all grain silos monitored by Grain Watch
get_spoilage_risk
Returns risk level (low, moderate, high, critical), contributing factors, predicted days until spoilage if conditions persist, and recommended preventive actions. Essential for proactive grain management, early intervention planning, and quality preservation. AI agents should use this when users ask "what is the spoilage risk for silo 3", "is silo 5 at risk of spoilage", or need AI-driven risk assessments for storage management decisions. Get AI-powered spoilage risk assessment for a specific silo
get_temperature_history
Temperature trends over time are critical for identifying developing hot spots, spoilage heating, or effective cooling from aeration. Returns time-series temperature data (Celsius) with timestamps from multiple sensor zones. Essential for hot spot detection, spoilage heating identification, aeration effectiveness evaluation, and grain quality preservation. AI agents should use this when users ask "show me temperature trends for silo 3 over the past 30 days", "has silo 5 been heating up", or need historical temperature data for storage condition analysis. Optional days parameter controls lookback period. Get historical temperature readings to detect trends and hot spot development
Example Prompts for Grain Watch in Mastra AI
Ready-to-use prompts you can give your Mastra AI agent to start working with Grain Watch immediately.
"Show me the current temperature readings for silo 3."
"Check for any hot spot alerts across my facility."
"Give me a facility-wide overview of all silo temperatures and any active alerts."
Troubleshooting Grain Watch MCP Server with Mastra AI
Common issues when connecting Grain Watch to Mastra AI through the Vinkius, and how to resolve them.
createMCPClient not exported
npm install @mastra/mcpGrain Watch + Mastra AI FAQ
Common questions about integrating Grain Watch MCP Server with Mastra AI.
How does Mastra AI connect to MCP servers?
MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.Can Mastra agents use tools from multiple servers?
Does Mastra support workflow orchestration?
Connect Grain Watch with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Grain Watch to Mastra AI
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.