How to Use the Cody AI MCP in OpenAI Agents SDK

Q: How do I register the Cody AI MCP Server in my OpenAI Agents SDK project?

Install the package with pip, then initialize the MCPServerStreamableHttp client pointing to your Vinkius endpoint. Wrap this in an async context manager and pass the server instance inside the mcpservers list when creating your Agent.

Q: Can my OpenAI Agents SDK setup handle multiple Cody bots?

Yes. The agent uses listbots to see everything available in your account. It then reads the details using getbotdetails to decide which specific bot fits the user's current support request.

Q: Does Cody AI support caching tool definitions to speed up OpenAI Agents SDK initialization?

Yes, you should set cacheToolsList=True in your connection parameters. This stops the SDK from fetching the schema on every single request, which shaves off startup latency.

Q: How do I track conversation history across different agent handoffs?

Use listmessages to pull the historical context of any active session. Your agents can read this thread history before using sendmessage to continue the chat, ensuring context isn't lost during handoffs.

Run secure Cody AI knowledge bots directly inside your OpenAI Agents SDK production workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cody AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Cody AI 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 Cody AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct OpenAI Agents SDK execution of Cody bots

Feed your production agents live knowledge from your Cody account without writing custom API wrappers or managing complex MCP schemas. Your agents auto-discover tools like `list_bots` and `get_bot_details` at startup, letting them choose the right bot for any customer inquiry on the fly. By configuring the `MCPServerStreamableHttp` client, your agent directly interacts with your knowledge bases. It can spin up sessions with `create_conversation` and route user queries to the exact bot trained on your product docs.

Live document feeding and status checks

Keep your customer support bots updated by ingestion of live web data. The agent triggers `import_webpage` when a user shares a link, pulling that new documentation straight into your knowledge base folders. To avoid answering based on stale or half-processed data, the agent runs `get_document_status` to verify the ingestion is complete. This runtime check ensures your agents only query bots that are fully trained on the latest uploads.

Managed conversation routing via MCP Server tools

Build multi-agent systems where one agent triages and another resolves. Using `list_conversations` and `list_messages`, your agents track the history of an issue before taking action. When the agent needs to generate a response, it uses `send_message` to query the trained bot. This keeps your conversation state centralized in Cody while your OpenAI agents handle the orchestration.

Setup guide

Set up Cody AI 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 Cody AI tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Cody AI 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="Cody AI Agent",
            instructions="You have access to Cody AI 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 Cody AI. 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 Cody AI 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 Cody AI MCP in OpenAI Agents SDK

Install the package with pip, then initialize the `MCPServerStreamableHttp` client pointing to your Vinkius endpoint. Wrap this in an async context manager and pass the server instance inside the `mcp_servers` list when creating your Agent.

Yes. The agent uses `list_bots` to see everything available in your account. It then reads the details using `get_bot_details` to decide which specific bot fits the user's current support request.

Yes, you should set `cacheToolsList=True` in your connection parameters. This stops the SDK from fetching the schema on every single request, which shaves off startup latency.

Use `list_messages` to pull the historical context of any active session. Your agents can read this thread history before using `send_message` to continue the chat, ensuring context isn't lost during handoffs.

Absolutely, your raw knowledge base documents and conversation logs never touch public LLM training sets. Vinkius runs the MCP server in an isolated, ephemeral sandbox that only handles the API requests to Cody, keeping your support files secure.

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