How to Use the ClearBank MCP in CrewAI

Deploy autonomous agent teams using CrewAI to monitor ClearBank ledgers and manage high-value UK payments.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClearBank MCP to CrewAI

Create your Vinkius account to connect ClearBank 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 ClearBank with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Ledger Auditing

`clearbank_get_transactions` enables your CrewAI audit specialist agent to pull historical ledger entries for deep financial analysis. While the auditor agent parses the transaction logs, a separate analyst agent uses the shared memory to calculate burn rates without leaving the MCP environment. This team-based approach allows your agents to cross-reference transactions against internal databases. They can flag discrepancies and compile compliance reports without human developers writing custom data-parsing code.

Autonomous Liquidity Management

`clearbank_get_account_balances` gives your CrewAI treasury manager agent the real-time visibility needed to rebalance corporate cash. When balances drop below a set threshold, the manager agent coordinates with a payment agent to execute a top-up. The payment agent then fires off `clearbank_create_faster_payment` to shift funds between your virtual accounts. This entire process occurs autonomously, maintaining healthy liquidity targets across all your UK ledgers.

Collaborative Incident Response with CrewAI

`clearbank_suspend_account` is invoked by your CrewAI security moderator agent the moment a threat is verified by the team. While the security agent freezes the account, a communications agent drafts an incident report for your Slack channel. The team verifies the status of pending transactions using `clearbank_get_payment_status` to determine which transfers were caught in the freeze. This ensures your operations team knows exactly which payments require manual reconciliation.

Setup guide

Set up ClearBank 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 ClearBank tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can use the MCPServerHTTP class from crewai.mcp and define a tool_filter. This lets you restrict sensitive tools like clearbank_suspend_account to security agents while letting analyst agents read balances.

Agents share data via CrewAI's built-in memory system. When an agent runs clearbank_get_transactions, the resulting JSON payload is indexed and made available to all other agents in the crew.

Yes, your CrewAI agent can check the current system time before running clearbank_create_chaps_payment. If it detects the Bank of England is closed, it will delegate the task to an agent configured to use Faster Payments.

The fastest method is passing your Vinkius endpoint URL directly into the agent's mcps array parameter. CrewAI handles the connection handshake and imports the active tools automatically.

All balance reports, account structures, and CHAPS/FPS payment instructions are shielded by end-to-end encryption. Our platform runs each multi-agent session in a hardened, ephemeral V8 sandbox that completely wipes all financial telemetry the moment your crew finishes executing.

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