How to Use the Veracode MCP in AutoGen

Q: Which Veracode tools are best for creating debate scenarios with AutoGen?

Use createapplication and deleteapplication in a controlled debate. One agent proposes a new app profile, and the other debates whether it should be created based on required compliance standards.

Q: Can I validate user access rights using Veracode and AutoGen?

Yes. An 'Auditor Agent' can run listveracodeusers to gather current roles. A 'Policy Agent' then debates if those roles meet the minimum required security standards, forcing a decision.

Q: What steps are needed before AutoGen uses Veracode tools?

You must first use listapplications to get the unique GUID. This ID is necessary context that both agents need before they can run any follow-up lookups on specific resources.

Build debate-driven security systems with Veracode and AutoGen's multi-agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Veracode MCP to AutoGen

Create your Vinkius account to connect Veracode 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 Veracode with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Facilitate automated threat modeling debates.

You can set up a debate where one agent uses `get_application_details` to identify high-risk scores, and another agent challenges that assessment by referencing the app's deployment state. The agents negotiate until they converge on a final risk decision.

Automate user permission negotiation.

Run `list_veracode_users` in one agent, and have a second agent validate those roles against policy best practices. This debate helps the system reach consensus on whether a new role needs to be added or if existing permissions are too broad.

Compare multiple security assessment results.

One agent can retrieve findings via `list_security_findings`, while another checks for active DAST scans using `list_dynamic_analyses`. Their discussion highlights discrepancies, like a high finding score existing even when the last scan was run.

Setup guide

Set up Veracode 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 Veracode 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="Veracode_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Veracode 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="Veracode_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Veracode 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 Veracode. 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 Veracode 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 Veracode MCP in AutoGen

The MCP Server allows different agents to debate using distinct tools. For example, a 'Risk Agent' calls `get_application_details`, and a 'Compliance Agent' calls `list_sandboxes` to challenge the risk score based on testing coverage.

Use `create_application` and `delete_application` in a controlled debate. One agent proposes a new app profile, and the other debates whether it should be created based on required compliance standards.

Yes. An 'Auditor Agent' can run `list_veracode_users` to gather current roles. A 'Policy Agent' then debates if those roles meet the minimum required security standards, forcing a decision.

You must first use `list_applications` to get the unique GUID. This ID is necessary context that both agents need before they can run any follow-up lookups on specific resources.

The server handles sensitive application profile status, including the business criticality rating. Agents must be carefully instructed to avoid debating or revealing unauthorized levels of this information.

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