How to Use the Deno Deploy MCP in AutoGen

Q: Can one AutoGen agent create a Deno Deploy app and another check it?

Yes, that's the core idea. The first agent calls createapp and shares the new app's ID in the conversation. The second agent then uses that ID with getapp or getapplogs to perform its checks, all within the AutoGen chat.

Let your AutoGen agents debate, manage, and deploy to Deno Deploy as a team.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deno Deploy MCP to AutoGen

Create your Vinkius account to connect Deno Deploy 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 Deno Deploy with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a multi-agent deployment committee

With AutoGen, you can assign different Deno Deploy tools to different agents to create checks and balances. A 'Developer' agent can propose a new release using `create_deployment`. But before it runs, a 'QA' agent must first inspect the build with `get_build_logs` and sign off. This creates a conversational workflow where agents must reach a consensus. The 'Developer' can't act alone. It needs approval from the 'QA' agent, which might demand more tests or log checks before giving the green light. You're building a process, not just running a command.

Debate infrastructure changes before they happen

Model real-world team discussions. An 'Engineer' agent might suggest creating a new application with `create_app` for a new service. A 'Finance' agent, armed with the `list_apps` tool, can push back, arguing that an existing app could be used instead to save costs. They can go back and forth, using tools to support their arguments. The 'Engineer' might use `get_app` to show resource constraints on an existing app, while the 'Finance' agent uses `get_organization` to check budget limits. The final decision is a result of their negotiation.

Assemble an automated incident response team

This MCP Server is perfect for building an AutoGen-powered response crew. One agent, the 'Monitor', constantly watches `get_app_logs` for errors. When it finds one, it brings in the 'Investigator' agent. The 'Investigator' uses `get_revision` and `get_build_logs` to diagnose what might have gone wrong in the last deployment. If it confirms a problem, it alerts a 'Rollback' agent, which can then use `create_deployment` to redeploy a known-good revision. It's a full incident lifecycle, handled by your agents.

Setup guide

Set up Deno Deploy 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 Deno Deploy 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="Deno Deploy_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You assign specific tools to each agent. For example, one agent has `create_deployment`, another has `get_app_logs`. The first agent must ask the second to verify the app's health before it's allowed to deploy, creating a collaborative, conversational workflow.

Yes, that's the core idea. The first agent calls `create_app` and shares the new app's ID in the conversation. The second agent then uses that ID with `get_app` or `get_app_logs` to perform its checks, all within the AutoGen chat.

Scripts follow a fixed path. AutoGen lets you model complex decision-making where the right answer isn't obvious. Your agents can debate the trade-offs of a deployment, just like a human team would, but in a fully automated way.

Definitely. You can have agents for operations, security, and finance that use tools like `list_projects`, `list_domains`, and `update_layer`. They can collaborate to ensure your Deno Deploy setup is efficient and secure.

Your agents will handle data like project names, deployment histories, and application logs. Each tool call is an isolated, authenticated transaction over HTTPS. The MCP server doesn't log or store any of your Deno Deploy data; it's passed directly to your agent.

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