How to Use the Argyle MCP in CrewAI

Q: Can I limit which Argyle tools a CrewAI agent can access?

Yes. Use the toolfilter option inside CrewAI's MCP server configuration. This allows you to restrict sensitive operations like createuser to your admin agent while letting other agents use getemployment.

Deploy specialized CrewAI agent teams to verify Argyle employment records and analyze payouts autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Argyle MCP to CrewAI

Create your Vinkius account to connect Argyle 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 Argyle with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent payroll checks in CrewAI

This MCP Server lets your CrewAI agents fetch employment history using `get_employment` and check `list_payouts` in parallel. One agent shouldn't do everything. With CrewAI, you can assign a researcher agent to fetch employment history while an analyst agent checks payouts. You connect the crew by adding the Vinkius endpoint directly to the agents' `mcps` array. Your specialized workers get immediate access to Argyle's real-time payroll data.

Automate user provisioning with this MCP Server

This MCP Server lets a specialized onboarding agent handle provisioning by calling `create_user` and verifying the link with `get_account_check`. Managing user accounts manually is a waste of engineering time. The agent can monitor the connection status and escalate to a support channel if the user fails to link their account. You can restrict tool access using the `MCPServerHTTP` class from `crewai.mcp`. This lets you expose `create_user` only to your onboarding specialist agent while keeping it hidden from analysis agents.

Analyze income trends using collaborative agents

This MCP Server allows your financial analysis crew to use `get_income` to pull salary structures and `list_identities` to confirm ownership. Raw payroll data is messy. A moderator agent then verifies the calculations before passing the report to your database. This setup removes human error from underwriting workflows. The agents execute their tasks sequentially, ensuring each step of the verification process is documented and checked.

Setup guide

Set up Argyle 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 Argyle tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius URL directly in the agent's definition using the `mcps` parameter. For advanced configurations, import `MCPServerHTTP` from `crewai.mcp` to filter which tools are available to specific agents.

Yes. Use the `tool_filter` option inside CrewAI's MCP server configuration. This allows you to restrict sensitive operations like `create_user` to your admin agent while letting other agents use `get_employment`.

CrewAI agents use shared memory to pass context. Once your researcher agent calls `get_income`, the resulting payout details are stored in the shared context, allowing the analyst agent to process the numbers immediately.

It supports stdio, SSE, and Streamable HTTP. The Vinkius managed gateway handles these protocols under the hood, so your python crew connects via a single secure endpoint.

Every request for employment or payout history runs inside an ephemeral sandbox. No data persists on the Vinkius platform, and all 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