How to Use the Deno Deploy MCP in OpenAI Agents SDK

Q: Does the OpenAI Agents SDK support Deno Deploy log streaming?

Yes. The server exposes getrevisionprogress via Server-Sent Events. Your Python agent reads the stream natively to track rollouts.

Q: Can OpenAI Agents SDK list my Deno Deploy projects?

Calling listprojects returns your organization data. The agent auto-discovers this tool immediately on startup.

Q: How do I isolate environments using this MCP Server?

Use the createlayer tool to manage environment variables. This keeps production and staging configurations entirely separate.

Manage your edge infrastructure with OpenAI Agents SDK. Deploy apps and stream logs through production-grade Python agents.

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 OpenAI Agents SDK

Create your Vinkius account to connect Deno Deploy to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ship Code with OpenAI Agents SDK

Calling `create_deployment` lets your agent push updates without breaking production. The system rolls out new revisions automatically based on your logic. We built this MCP Server to handle the raw API calls so your Python code focuses entirely on business rules. Guardrails matter when infrastructure is on the line. The agent runs `get_revision` to verify a deployment succeeded before moving on to the next task. Handoffs work perfectly here, where one specialized agent writes the code and another handles the actual rollout steps.

Monitor Edge Deployments

Exposing `get_build_logs` gives your agent direct access to deployment failures. It reads exactly what broke during the build step and reports back. You get the full trace right inside your OpenAI dashboard without opening another tab. Fetching runtime errors happens through `get_app_logs`. The system parses these logs and suggests fixes before a human even wakes up. Setting cacheToolsList to true keeps the MCP auto-discovery fast during these debugging loops.

Manage Organization Projects

Your agent uses `create_layer` to enforce strict boundaries across multiple environments. It shares specific environment variables across targeted projects. Secrets never leak to the wrong application. Listing current domains via `list_domains` gives the system context about what is already live. You just pass the Vinkius endpoint token into the MCPServerStreamableHttp constructor. Everything stays sandboxed safely inside our V8 isolates.

Setup guide

Set up Deno Deploy MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Deno Deploy tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Deno Deploy tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Deno Deploy tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Deno Deploy Agent",
            instructions="You have access to Deno Deploy tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package via pip. Then initialize MCPServerStreamableHttp with your Vinkius MCP endpoint URL. Pass it to the Agent constructor in the mcp_servers array.

Yes. The server exposes `get_revision_progress` via Server-Sent Events. Your Python agent reads the stream natively to track rollouts.

Calling `list_projects` returns your organization data. The agent auto-discovers this tool immediately on startup.

Use the `create_layer` tool to manage environment variables. This keeps production and staging configurations entirely separate.

Vinkius runs this tool inside an ephemeral V8 isolate. The agent only accesses the specific apps, build logs, and environment variables you authorize. We drop the sandbox the second your session ends.

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