How to Use the KeyPay MCP in CrewAI

Q: How do I add KeyPay tools to a CrewAI agent?

Pass your Vinkius endpoint URL directly into the mcps array when defining the agent. The framework automatically discovers and registers all ten available endpoints.

Q: How do I restrict which KeyPay tools a CrewAI agent can use?

Import MCPServerHTTP from crewai.mcp. Use the toolfilter parameter to limit an agent to specific actions, like only allowing access to leave requests.

Deploy autonomous payroll teams to manage KeyPay records using CrewAI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KeyPay MCP to CrewAI

Create your Vinkius account to connect KeyPay 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 KeyPay with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit payroll cycles with CrewAI teams

The `list_pay_runs` and `get_pay_run_details` tools feed historical payroll data to your financial analyst agent. This agent reads the cycle dates and identifies anomalies. You can assign a second auditor agent to verify the findings. They share memory. The first agent finds an odd pay run, and the second agent independently checks the numbers before alerting human resources.

Investigate employee pay slips autonomously

Give your support agent access to the `list_pay_slips` and `list_employees` tools. When a worker asks about their last paycheck, the agent searches the directory and pulls the specific document. The operation runs hierarchically. A manager agent receives the initial query, delegates the search task to the support agent, and formats the final response based on the retrieved data.

Monitor leave balances across businesses

Using `list_businesses` and `list_leave_requests`, an oversight agent scans all connected companies for excessive time-off balances. The MCP Server handles the cross-account routing. You build this without writing custom API polling scripts. The crew operates on a schedule, pulls the latest requests, and compiles a daily briefing for the payroll administrator.

Setup guide

Set up KeyPay 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 KeyPay tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent KeyPay 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="KeyPay Analyst",
        goal="Access and analyze KeyPay data via MCP.",
        backstory="Expert analyst with direct KeyPay access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent KeyPay 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 KeyPay. 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 KeyPay 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 KeyPay MCP in CrewAI

Pass your Vinkius endpoint URL directly into the `mcps` array when defining the agent. The framework automatically discovers and registers all ten available endpoints.

Yes. You can assign the same MCP Server to an entire crew. A researcher agent can pull employee data while a reporter agent formats the output.

Import `MCPServerHTTP` from `crewai.mcp`. Use the `tool_filter` parameter to limit an agent to specific actions, like only allowing access to leave requests.

No. The protocol exposes the operations directly to the LLM. Your agents understand the required parameters and execute the calls natively.

Vinkius manages routing without inspecting payloads. When your crew fetches `list_pay_slips`, the sensitive financial records travel straight to your Python environment through a secure, stateless tunnel.

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