How to Use the Harvest MCP in Mastra AI

Q: How do I register the Harvest MCP Server tools with a Mastra AI agent?

Instantiate the MCPClient with your Vinkius endpoint URL. You then fetch the available tools using mcpClient.listTools() and spread them directly into your agent configuration object.

Q: How do I restrict access to the client deletion tools in Mastra AI?

You use Mastra's requireToolApproval option to block the deleteclient tool. This forces the system to request manual human confirmation before any client record is permanently erased.

Q: Can I run multi-step invoicing loops with these tools?

Absolutely. You can build a workflow that calls listinvoices to find unpaid drafts, processes the totals, and then triggers createinvoice to generate the next cycle's draft.

Build resilient agent workflows that automate your Harvest invoicing and client updates with Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harvest MCP to Mastra AI

Create your Vinkius account to connect Harvest to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Harvest with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automating invoice runs with Mastra AI workflows

The `create_invoice` tool provides the core action for your automated billing cycles using this MCP Server. If an invoice generation fails, Mastra AI uses its built-in retry engine to execute the call again with exponential backoff. This ensures your billing runs complete even during network hiccups. You define conditional branches that trigger after the invoice draft is ready. The workflow checks the output, then proceeds to notify your team or update internal records automatically. It eliminates manual intervention from your billing routine.

Resilient customer syncs using Mastra AI agents

The `create_client` tool allows your Mastra AI agent to register new customers during onboarding workflows using our managed MCP. When a client record needs modifications, the `update_client` tool applies those changes inside the same execution block. This keeps your records synchronized across your CRM and accounting platforms. You configure human-in-the-loop approvals before executing these database changes. The agent pauses, waits for an admin signature, and then applies the update. This step prevents accidental data overwrites.

Deep project audits via the Mastra AI engine

The `list_projects` tool pulls project indexes into your multi-step workflows to verify active engagements. Your agent uses this list to cross-reference work hours across your entire team. It flags projects that are nearing their budget limits before issues arise. By combining this with `list_time_entries`, the agent calculates exact utilization rates. Mastra AI processes these large datasets in memory, preparing structured reports for your leadership team. It takes the guesswork out of resource planning.

Setup guide

Set up Harvest 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 Harvest 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: "harvest-mcp-client",
  servers: {
    "harvest-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Harvest 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 Harvest. 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 Harvest 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 Harvest MCP in Mastra AI

Instantiate the `MCPClient` with your Vinkius endpoint URL. You then fetch the available tools using `mcpClient.listTools()` and spread them directly into your agent configuration object.

Yes. Mastra AI uses automatic retries with exponential backoff when executing `list_time_entries`. If the API returns a rate-limit error, the engine pauses and retries the request without failing the workflow.

You use Mastra's `requireToolApproval` option to block the `delete_client` tool. This forces the system to request manual human confirmation before any client record is permanently erased.

Absolutely. You can build a workflow that calls `list_invoices` to find unpaid drafts, processes the totals, and then triggers `create_invoice` to generate the next cycle's draft.

All time entries and client details are processed within an ephemeral, memory-only sandbox. No data persists on our servers, and your credentials are encrypted end-to-end to prevent unauthorized access.

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