How to Use the Convai MCP in OpenAI Agents SDK

Q: How do I set up the Convai MCP Server with the OpenAI Agents SDK?

Install openai-agents, then instantiate MCPServerStreamableHttp using the Vinkius endpoint URL. Pass this server instance directly into your Agent constructor's mcpservers list to let your agent auto-discover the tools.

Q: Can my OpenAI Agents SDK pipeline update character knowledge banks in Convai?

Yes. Your agent can use uploadknowledgebank and updateknowledgebank to modify what an NPC remembers. This lets you dynamically feed new documents or lore files to your characters during runtime.

Q: How do I debug tool calls made by this server?

You can use getprompt to fetch raw prompt data for debugging. Additionally, the OpenAI developer dashboard provides full tracing for every tool execution, letting you inspect inputs and outputs instantly.

Build, test, and deploy interactive Convai game characters directly inside your OpenAI Agents SDK production pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convai MCP to OpenAI Agents SDK

Create your Vinkius account to connect Convai 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 Convai with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control Convai Characters via OpenAI Agents SDK

The Convai MCP Server lets your OpenAI Agents SDK codebase programmatically spin up and modify game entities without manual dashboard clicking. You can run `create_character` to instantiate a brand-new NPC, then feed it a custom backstory with `generate_backstory` on the fly. Instead of hardcoding dialogue trees, your agents use these tools to build dynamic personalities based on real-time player interactions. This makes your NPCs feel alive instead of sounding like static text trees.

Manage Narrative Triggers with Built-in Guardrails

This MCP Server exposes direct control over the story state, allowing your agent to toggle narrative-driven modes on demand. By calling `toggle_narrative` and `create_narrative_trigger`, your pipeline dynamically shifts what an NPC knows or how they react as the player progresses. OpenAI Agents SDK handles the safety side, tracing these tool executions on your dashboard so you can verify that the agent doesn't trigger incorrect story states. If an agent tries to jump ahead, your built-in guardrails catch it before it hits production.

Evaluate Live Conversations and Chat Logs

The integration lets your system run automated quality checks on player interactions using `evaluate_conversation` and `get_chat_session_details`. Your agent pulls the raw transcripts, analyzes the player's choices, and rates the dialogue based on your custom metrics. Because OpenAI Agents SDK supports clean handoffs between specialized agents, you can have one agent manage the live game session while a background agent runs these evaluations. It keeps your live gameplay fast while maintaining a deep log of player behavior.

Setup guide

Set up Convai 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 Convai tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents`, then instantiate `MCPServerStreamableHttp` using the Vinkius endpoint URL. Pass this server instance directly into your Agent constructor's `mcp_servers` list to let your agent auto-discover the tools.

Yes. Your agent can use `upload_knowledge_bank` and `update_knowledge_bank` to modify what an NPC remembers. This lets you dynamically feed new documents or lore files to your characters during runtime.

Yes, absolutely. You can design one agent to build characters using `create_character` and then hand off the session to a separate specialized agent that manages narrative progression via this MCP server.

You can use `get_prompt` to fetch raw prompt data for debugging. Additionally, the OpenAI developer dashboard provides full tracing for every tool execution, letting you inspect inputs and outputs instantly.

Your character voice files and transcripts are processed in an ephemeral V8 Isolate sandbox on Vinkius. No data is stored on our servers, and all API calls to Convai are secured using your single endpoint token.

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