How to Use the Denim MCP in AutoGen

Q: How do I add Denim MCP tools to an AutoGen agent?

Install autogen-extmcp and use mcpservertools with your Denim connection URL. Pass the resulting tool list to your AssistantAgent constructor to give them access to campaign management.

Q: Can AutoGen agents collaborate to update Denim contacts?

Yes, a lead-scoring agent can analyze a contact from listcrmcontacts, and if the score is high enough, instruct a writer agent to trigger addnewcontact to add them to a high-priority campaign list.

Q: How do AutoGen agents handle Denim API failures?

If a tool like listactiveautomations fails or returns an error, the executing agent communicates the issue back to the group. The coordinator agent can then decide to retry or check getaccountmetadata to see if you hit an API limit.

Q: How does AutoGen protect my Denim campaign settings?

All API keys and campaign configurations handled by getcampaigndetails are kept secure. Vinkius runs the Denim MCP connection in an ephemeral V8 sandbox, preventing agents from leaking your raw API credentials during their multi-turn debates.

Let AutoGen agents debate and optimize your Denim marketing campaigns before they launch.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Denim MCP to AutoGen

Create your Vinkius account to connect Denim 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 Denim with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate over Denim campaign performance

The Denim MCP Server enables your AutoGen agents to debate campaign performance using live marketing metrics. One agent pulls performance data using `get_campaign_analytics` while the other checks limits via `get_account_metadata`. They debate the best path forward. Instead of blindly running campaigns, they negotiate whether to adjust active workflows found in `list_active_automations` based on real-time performance.

Consensus-driven contact management via AutoGen

This Denim integration allows your AutoGen team to collaborate on contact validation before updating your database. A validation agent can inspect new lead data, while a database agent runs `search_active_campaigns` to see if the contact is already receiving emails. Only when both agents agree does the system call `add_new_contact`. This consensus-driven approach prevents duplicate emails and keeps your Denim CRM database pristine.

Collaborative template selection using this MCP Server

The Denim MCP Server lets your AutoGen agents work together to select and verify email templates. A creative agent pulls options using `list_email_templates`, while an analyst agent looks at historical success rates using `get_campaign_details`. They discuss which template fits the target audience segment retrieved from `list_audience_segments`. Once they agree, they hand the final configuration off to your execution agent.

Setup guide

Set up Denim 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 Denim 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="Denim_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp] and use mcp_server_tools with your Denim connection URL. Pass the resulting tool list to your AssistantAgent constructor to give them access to campaign management.

Yes, a lead-scoring agent can analyze a contact from `list_crm_contacts`, and if the score is high enough, instruct a writer agent to trigger `add_new_contact` to add them to a high-priority campaign list.

If a tool like `list_active_automations` fails or returns an error, the executing agent communicates the issue back to the group. The coordinator agent can then decide to retry or check `get_account_metadata` to see if you hit an API limit.

Yes, AutoGen's MCP adapter works with both stdio and Streamable HTTP transports. You can connect your multi-agent team to the Denim server hosted on Vinkius using a single secure HTTP endpoint.

All API keys and campaign configurations handled by `get_campaign_details` are kept secure. Vinkius runs the Denim MCP connection in an ephemeral V8 sandbox, preventing agents from leaking your raw API credentials during their multi-turn debates.

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