How to Use the Bolt MCP in CrewAI

Q: How do CrewAI agents share Bolt transaction details during a run?

They pass the outputs of tools like gettransaction through CrewAI's shared memory. One agent fetches the payment details, and the next agent immediately reads that context to decide the next action.

Q: What happens if a Bolt checkout token expires during execution?

Your agent will receive an error from createordertoken. You should write a conditional task in your crew's pipeline to automatically request a fresh token if the first one fails.

Put your CrewAI agents in charge of your Bolt checkout loops to capture transactions and trigger refunds autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bolt MCP to CrewAI

Create your Vinkius account to connect Bolt 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 Bolt with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Bolt refund loops with CrewAI agents

This Bolt MCP Server gives your multi-agent teams the exact tools they need to resolve checkout disputes and handle payment errors without human intervention. Your support agent can read the incoming complaint, while a finance agent runs `get_transaction` and `get_order_details` to verify the purchase status in seconds. If the claim checks out, the finance agent triggers `refund_transaction` or `void_transaction` based on whether the charge settled. The whole crew coordinates through shared memory, keeping your books clean and your customers happy without a single manual click.

Let CrewAI agents generate checkout links

Generating active checkout sessions is straightforward once you plug this Bolt server into your execution pipelines. When a customer agent requests a custom bundle, the inventory agent checks stock levels and hands off the task to a checkout agent to run `create_order_token`. This token gets passed back to the customer instantly. By running these tasks sequentially, your crew handles the entire purchase flow from demand generation to payment readiness in a single loop.

Monitor merchant health using an MCP Server crew

Keeping a constant eye on store cash flow becomes automated when you deploy a dedicated operations crew. A monitoring agent runs `get_merchant_status` and `list_webhooks` to ensure your gateway is active and listening for payment events. Meanwhile, a reporting agent pulls the latest data using `list_transactions` and `get_account_details` to flag any sudden drops in checkout completion rates. The agents escalate anomalies to your Slack channel before your customers even notice an issue.

Setup guide

Set up Bolt 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 Bolt tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install CrewAI with the tools package using pip. After that, pass your Vinkius endpoint URL directly into the `mcps` array when defining your agents.

Only if you configure your crew's roles and tools to allow it. You can restrict access to `refund_transaction` by using a tool filter in your server configuration.

They pass the outputs of tools like `get_transaction` through CrewAI's shared memory. One agent fetches the payment details, and the next agent immediately reads that context to decide the next action.

Your agent will receive an error from `create_order_token`. You should write a conditional task in your crew's pipeline to automatically request a fresh token if the first one fails.

Yes, because Vinkius runs this MCP Server inside a zero-trust, ephemeral V8 isolate sandbox. Your raw credentials and payment transactions never touch external logs or persistent databases, keeping your checkout data isolated.

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