How to Use the ngrok MCP in CrewAI

Q: How do I load the ngrok MCP Server into CrewAI?

Run pip install crewaitools. You can pass the Vinkius endpoint directly into the mcps array on your Agent definition. The framework handles the connection automatically.

Q: Can I restrict which ngrok tools my CrewAI agent sees?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. This lets you give one agent access to listendpoints while blocking it from seeing listvaults.

Deploy specialized CrewAI agents to autonomously monitor and audit your ngrok network edges.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ngrok MCP to CrewAI

Create your Vinkius account to connect ngrok 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 ngrok with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit ngrok edges with CrewAI

Security operations require constant vigilance. You can assign this MCP Server to a dedicated auditor agent within your CrewAI setup. The agent uses `list_https_edges` to find active public URLs, then passes that list to a specialized analyst agent. Shared memory keeps the crew aligned. The analyst reviews the edges and asks the auditor to pull `list_ip_policies` for specific tunnels. Because the agents collaborate hierarchically, they piece together a complete map of your exposed infrastructure without waiting for a human to run Python scripts.

Delegate API key tracking

Tracking who owns which access token is a massive pain. You configure a monitor agent with the `list_api_keys` tool and instruct it to check for stale credentials every morning. The agent grabs the data and writes a summary report. If the monitor finds something suspicious, it escalates. The workflow triggers a moderator agent to investigate further. The moderator might execute `list_vaults` to see if the compromised key has access to sensitive certificate storage, operating entirely autonomously based on the initial findings.

Map hidden developer tunnels

Developers spin up local tunnels and forget them. A discovery agent running on a sequential CrewAI pipeline can execute `list_endpoints` to find these orphaned connections. It cross-references the active endpoints against your approved internal project list. The crew handles the heavy lifting. Once the discovery agent maps the endpoints, it calls `list_reserved_domains` to see if anyone attached a production URL to a local machine. The final output is a clean text file detailing exactly which developer laptops are exposing internal services.

Setup guide

Set up ngrok 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 ngrok tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Run `pip install crewai[tools]`. You can pass the Vinkius endpoint directly into the `mcps` array on your Agent definition. The framework handles the connection automatically.

Yes. Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. This lets you give one agent access to `list_endpoints` while blocking it from seeing `list_vaults`.

It supports multiple transports natively. You can use standard stdio, SSE, or Streamable HTTP depending on how you configure the Vinkius connection URL.

CrewAI uses shared memory. When your discovery agent pulls the active endpoints, the analyst agent can read that exact same dataset from memory without making a redundant API call.

The system restricts exposure entirely to your local Python environment. When the agent calls `list_api_keys`, Vinkius routes the request through a stateless, isolated sandbox. The credential strings travel securely to your machine, and the server destroys the memory instance immediately after the HTTP response completes.

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