How to Use the Conduit MCP in CrewAI

Q: How do I add the Conduit MCP Server to a CrewAI agent?

Pass your Vinkius HTTP endpoint directly into the agent's mcps parameter during initialization. For more control, use MCPServerHTTP from crewai.mcp to connect the MCP Server and specify a toolfilter to limit which agents can run specific tools.

Q: Can CrewAI agents autonomously trigger a Conduit pipeline?

Yes. Your operator agent can call triggerworkflow after a research agent finds the correct workflow ID using listworkflows. CrewAI manages the tool execution and shares the result across the crew's memory.

Q: How do CrewAI agents share Conduit pipeline status?

CrewAI uses shared memory, so when one agent calls getrunstatus, the resulting JSON payload is accessible to other agents in the crew. This allows an analyst agent to inspect the run details without re-running the tool.

Q: Does this server support restricted tool access for CrewAI?

Yes. You can use the MCPServerHTTP class to apply a toolfilter. This ensures only your designated operator agent has access to write operations like triggerworkflow, while others only monitor.

Deploy multi-agent teams in CrewAI to autonomously monitor, audit, and trigger your Conduit pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conduit MCP to CrewAI

Create your Vinkius account to connect Conduit 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 Conduit with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Pipeline Auditing in CrewAI

The `list_workflows` tool serves as the starting point for your auditor agent to discover active pipelines. Using this MCP Server, the auditor agent gathers these IDs and passes them to the analyst agent to check for anomalies. The analyst agent then uses `get_workflow` to inspect source and destination configurations. This multi-agent collaboration ensures your data pipelines comply with infrastructure rules without manual developer oversight.

Multi-Agent Incident Response for Conduit

The `list_workflow_runs` tool allows your monitoring agent to track the execution history of all active pipelines. If this agent spots a failed run, it alerts your operator agent to take immediate action. The operator agent calls `get_run_status` to diagnose the failure, then uses `trigger_workflow` to restart the pipeline. This entire loop runs autonomously within your CrewAI memory space, keeping your pipelines running 24/7.

Autonomous Connector Configuration Audits

The `list_available_sources` tool gives your research agent visibility into all data sources supported by your infrastructure. The agent cross-references this with `list_available_destinations` to map potential data paths. Using this information, the crew writes configuration proposals or flags unused active connections. By invoking `list_connections`, the agents verify that your actual running setup matches your desired architectural state.

Setup guide

Set up Conduit 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 Conduit tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius HTTP endpoint directly into the agent's `mcps` parameter during initialization. For more control, use `MCPServerHTTP` from `crewai.mcp` to connect the MCP Server and specify a `tool_filter` to limit which agents can run specific tools.

Yes. Your operator agent can call `trigger_workflow` after a research agent finds the correct workflow ID using `list_workflows`. CrewAI manages the tool execution and shares the result across the crew's memory.

CrewAI uses shared memory, so when one agent calls `get_run_status`, the resulting JSON payload is accessible to other agents in the crew. This allows an analyst agent to inspect the run details without re-running the tool.

Yes. You can use the `MCPServerHTTP` class to apply a `tool_filter`. This ensures only your designated operator agent has access to write operations like `trigger_workflow`, while others only monitor.

All connection strings, API tokens, and sync logs are handled within the secure Vinkius V8 sandbox. Your CrewAI agents interact with the MCP Server via encrypted HTTP endpoints, ensuring sensitive pipeline details never leak.

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