How to Use the Equixly MCP in AutoGen

Q: How can an AutoGen workflow use Equixly to find and verify vulnerabilities?

Assign the Equixly tools to an AssistantAgent. It calls triggerscan and getscanfindings. A second agent, without the tools, receives the findings and asks clarifying questions, forcing the first agent to double-check its work before reporting to the user.

Q: How do I give only one agent in my AutoGen group access to tools like deleteservice?

When you define your agents, you pass the mcpservertools list only to the specific AssistantAgent you want to have those permissions. Other agents in the conversation won't be able to see or call deleteservice.

Let your AutoGen agents debate and decide on API security risks, using live pentest data from Equixly to drive consensus.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Equixly MCP to AutoGen

Create your Vinkius account to connect Equixly to AutoGen 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 Equixly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create an Automated Security Review Board

Go beyond simple automation and build a team of agents. Create a "SecurityAnalyst" agent that uses `trigger_scan` and `get_scan_findings` to find flaws. Then, create a "DevOpsEngineer" agent that cares about deployment velocity. When the SecurityAnalyst flags a medium-severity issue, the DevOpsEngineer can argue that it's in a non-critical service (verified with `get_service`) and shouldn't block the release. They debate using the Equixly tool outputs as evidence until they reach a consensus.

Negotiate Remediation Priorities with AutoGen

A single agent might just dump a list of bugs. A multi-agent system can prioritize them. Your "ProductManager" agent can ask for a scan of a new feature branch using `trigger_scan`. Once the "SecurityAnalyst" agent gets the report via `get_scan_findings`, the two agents can discuss the findings. The PM might argue a UI bug is low priority, while the analyst insists an injection flaw is a showstopper. This conversation produces a prioritized backlog, not a raw data dump.

Let Agents Manage the Attack Surface

Set up a conversation between a "ServiceRegistry" agent and a "SecurityOps" agent. The first agent's job is to monitor your infrastructure. The second agent's job is to ensure everything is scanned using this MCP server. When the registry agent detects a new service, it informs the SecurityOps agent, which then uses `create_service` and `upload_api_spec` to add it to Equixly. If an API is retired, one agent can use `delete_service` and inform the others. It's a self-governing system.

Setup guide

Set up Equixly MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Equixly tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Equixly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Equixly data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Equixly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Equixly data")
    print(result.messages[-1].content)

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 Equixly. 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 Equixly 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 Equixly MCP in AutoGen

Assign the Equixly tools to an `AssistantAgent`. It calls `trigger_scan` and `get_scan_findings`. A second agent, without the tools, receives the findings and asks clarifying questions, forcing the first agent to double-check its work before reporting to the user.

Yes. You'd configure two different scan profiles in Equixly. Your agent could use `get_service` to check the environment, then decide which scan profile to pass to the `trigger_scan` tool based on whether it's a staging or production system.

AutoGen lets you model real-world team debates. With Equixly, your agents aren't just talking; they're arguing with facts. One agent can present hard evidence from `get_scan_findings`, forcing other agents to justify their positions, leading to better, consensus-driven security decisions.

When you define your agents, you pass the `mcp_server_tools` list only to the specific `AssistantAgent` you want to have those permissions. Other agents in the conversation won't be able to see or call `delete_service`.

Yes. The Equixly MCP server sends vulnerability findings directly to your agent over an encrypted connection. Vinkius processes the tool call in a dedicated, ephemeral environment, ensuring your scan results aren't exposed or persisted on the server side.

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