How do I find my Harvest Access Token and Account ID?

Go to the **Harvest Developers** site (id.getharvest.com), navigate to **Personal Access Tokens**, and create a new token. You will find both the **token** and the **Account ID** listed there.

Can I see time entries for a specific period?

Yes! Use the `list_time_entries` tool and provide the `from` and `to` dates in YYYY-MM-DD format to retrieve records for that timeframe.

Is it possible to create invoices through this integration?

Yes, you can use the `create_invoice` tool by providing a `client_id` and an optional `subject` to generate a new invoice draft in your Harvest account.

Is the integration secure for managing financial data?

Absolutely. The integration uses official Harvest API tokens over HTTPS. Your credentials are encrypted and stored securely within the Vinkius Cloud infrastructure.

Harvest MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: Harvest
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Harvest through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Harvest "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Harvest?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Harvest MCP Server

Connect your Harvest account to any AI agent and take full control of your time tracking, client management, and invoicing through natural conversation.

Pydantic AI validates every Harvest tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Time Tracking Oversight — List and inspect tracked time entries to monitor team productivity.
Client Management — List all clients, create new ones, and update company details effortlessly.
Invoicing Automation — Access your invoice history, create new drafts, and manage billing statuses.
Project Monitoring — List all active projects and retrieve detailed information for each.
User Profile — Get information about the current authenticated user and account status.
Operational Efficiency — Use AI to identify unbilled time or upcoming invoice deadlines across your organization.

The Harvest MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic 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 Harvest to Pydantic AI via MCP

Follow these steps to integrate the Harvest MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 11 tools from Harvest with type-safe schemas

Why Use Pydantic AI with the Harvest MCP Server

Pydantic AI provides unique advantages when paired with Harvest through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Harvest integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Harvest connection logic from agent behavior for testable, maintainable code

Harvest + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Harvest MCP Server delivers measurable value.

Type-safe data pipelines: query Harvest with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Harvest tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Harvest and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Harvest responses and write comprehensive agent tests

Harvest MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect Harvest to Pydantic AI via MCP:

create_client

Create a new client in Harvest

create_invoice

Create a new invoice for a client

delete_client

Permanently delete a client

get_client

Get detailed information for a specific client

get_invoice

Get details for a specific invoice

get_my_profile

Get information about the current authenticated user

list_clients

List all clients in your Harvest account

list_invoices

List all invoices, including drafts and sent ones

list_projects

List all projects in the account

list_time_entries

List tracked time entries

update_client

Update an existing client name

Example Prompts for Harvest in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Harvest immediately.

"List all time entries from last week."

"Create a new client named 'Acme Corp'."

"Show me all active projects."

Troubleshooting Harvest MCP Server with Pydantic AI

Common issues when connecting Harvest to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Harvest + Pydantic AI FAQ

Common questions about integrating Harvest MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Harvest MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.