How to Use the Harvest MCP in CrewAI

Q: How do I add the Harvest MCP Server to a CrewAI agent?

You pass your Vinkius server URL directly into the agent's mcps array parameter. The framework automatically parses the endpoints and exposes the billing tools to that specific agent.

Q: Can CrewAI agents collaborate on Harvest time tracking via MCP?

Yes. One agent can use listtimeentries to gather hours, while another agent uses listprojects to match those hours to specific budgets. They share this data through CrewAI's internal memory.

Q: How do I limit which tools a specific CrewAI agent can use?

Use the MCPServerHTTP class with a toolfilter to restrict access. This prevents a research agent from executing deleteclient while allowing your accounting agent to run it.

Deploy specialized CrewAI agent teams to audit time entries and generate Harvest invoices automatically.

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 CrewAI

Create your Vinkius account to connect Harvest to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent billing teams with CrewAI and Harvest

The `list_time_entries` tool gives your CrewAI agents direct access to raw tracked hours via this MCP setup. You can assign a specialized auditor agent to pull these entries and check them against project budgets. This division of labor ensures high accuracy before any invoices are drafted. Once the auditor agent approves the hours, a billing agent uses `create_invoice` to draft the final bill. This multi-step process mimics a real accounting department. It keeps your billing operations running autonomously.

Autonomous client onboarding using CrewAI teams

The `create_client` tool lets your customer success crew register new accounts without human intervention. The onboarding agent checks incoming emails, extracts company info, and registers the client profile. This removes administrative bottlenecks from your sales pipeline. If details change, a moderator agent triggers `update_client` to correct the company name. The agents share context through CrewAI's memory features, keeping all team members aligned. It ensures your CRM and billing directories stay perfectly synchronized.

Automated project health monitoring via MCP Server

The `list_projects` tool allows your monitoring crew to track active engagements. A supervisor agent pulls the list of active projects and assigns individual task-tracking agents to analyze them. This setup helps you spot stalling projects before they impact your cash flow. The agents use `get_invoice` to verify which milestones have been billed. By comparing invoiced amounts with logged hours, your crew alerts you to unbilled work instantly. It protects your agency from revenue leakage.

Setup guide

Set up Harvest MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Harvest tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Harvest Analyst",
    goal="Access and analyze Harvest data via MCP.",
    backstory="Expert analyst with direct Harvest access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Harvest transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Harvest Analyst",
        goal="Access and analyze Harvest data via MCP.",
        backstory="Expert analyst with direct Harvest access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Harvest transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You pass your Vinkius server URL directly into the agent's `mcps` array parameter. The framework automatically parses the endpoints and exposes the billing tools to that specific agent.

Yes. One agent can use `list_time_entries` to gather hours, while another agent uses `list_projects` to match those hours to specific budgets. They share this data through CrewAI's internal memory.

Use the `MCPServerHTTP` class with a `tool_filter` to restrict access. This prevents a research agent from executing `delete_client` while allowing your accounting agent to run it.

CrewAI's execution engine catches the failure and allows the agent to retry or ask another crew member for help. This prevents your entire automation pipeline from crashing due to a single API timeout.

All project budgets, client profiles, and billing logs are transmitted through secure, ephemeral V8 isolates. Your sensitive business data is never stored, cached, or used for model training.

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