How to Use the Griffin MCP in CrewAI

Q: How do I configure the Griffin MCP Server in CrewAI?

Install crewai and crewaitools to connect the Griffin server to your agent team. You can pass your server URL directly to the agent's mcps list, or use MCPServerHTTP from crewai.mcp to filter specific tools like listtransactions for individual agents.

Q: How do CrewAI agents verify organization details using Griffin?

Your agents can use listorganizations to map the corporate structure. A coordinator agent then uses getorganization to verify the active status of the entity before delegating banking tasks to other crew members.

Q: Can a security agent check the identity of the API caller?

Yes, your security agent can run getme to verify the authenticated user's details. This ensures the CrewAI agent is operating under the correct credentials before accessing sensitive financial data.

Q: How is sensitive compliance data protected?

All data fetched via getverification is processed inside Vinkius's secure V8 isolates. The CrewAI framework executes tools locally or over encrypted HTTPS, ensuring sensitive compliance records are never exposed to public networks.

Deploy specialized CrewAI agent teams to manage Griffin bank ledgers and compliance checks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Griffin MCP to CrewAI

Create your Vinkius account to connect Griffin 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 Griffin with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent ledger audits with CrewAI

This MCP Server gives your CrewAI agent teams direct access to Griffin bank ledger histories. An auditor agent can call `list_transactions` to pull recent activity, while a compiler agent organizes the data into reports. The CrewAI agents share memory to spot discrepancies. If an issue is found, a moderator agent uses `get_transaction` to pull the full details and flags the record for manual review without stopping the overall workflow.

Autonomous KYC review pipelines with CrewAI

This MCP Server allows specialized compliance crews in CrewAI to handle user onboarding. A verifier agent calls `list_verifications` to fetch pending background checks and evaluates the risk profile. Once the evaluation is complete, the CrewAI agent uses `get_verification` to retrieve specific user data. Another agent can then document the decision, keeping your onboarding pipeline moving without human intervention.

Automated treasury management crews with CrewAI

This MCP Server lets CrewAI teams manage cash flow across multiple Griffin accounts. A monitor agent uses `list_accounts` to track balances, detecting when funds run low in specific ledgers. When a balance falls below your threshold, a treasurer agent calls `create_internal_transfer` to rebalance the accounts. The entire CrewAI crew coordinates to maintain liquidity without manual intervention.

Setup guide

Set up Griffin 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 Griffin tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install `crewai` and `crewai[tools]` to connect the Griffin server to your agent team. You can pass your server URL directly to the agent's `mcps` list, or use `MCPServerHTTP` from `crewai.mcp` to filter specific tools like `list_transactions` for individual agents.

Yes, CrewAI agents use shared memory to pass context. When one agent calls `get_account` to fetch ledger details, that information is available to other agents in the crew to make informed decisions about transfers.

Your agents can use `list_organizations` to map the corporate structure. A coordinator agent then uses `get_organization` to verify the active status of the entity before delegating banking tasks to other crew members.

Yes, your security agent can run `get_me` to verify the authenticated user's details. This ensures the CrewAI agent is operating under the correct credentials before accessing sensitive financial data.

All data fetched via `get_verification` is processed inside Vinkius's secure V8 isolates. The CrewAI framework executes tools locally or over encrypted HTTPS, ensuring sensitive compliance records are never exposed to public networks.

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