How to Use the DocsBot MCP in OpenAI Agents SDK

Q: How do I register the DocsBot MCP Server within my OpenAI Agents SDK pipeline?

Install the package using pip install openai-agents. Next, initialize the connection using MCPServerStreamableHttp with your Vinkius endpoint, and pass it to your Agent constructor inside the mcpservers list. Set cacheToolsList=True to keep your production runs fast.

Q: Can OpenAI Agents SDK handle multi-agent handoffs when querying different DocsBot instances?

Yes, you can design a supervisor agent that calls listteambots to locate the right bot for a specific user query. Once the supervisor identifies the correct bot, it passes the context to a specialized agent that executes askbotquestion.

Q: How can I trace DocsBot API calls made by my OpenAI Agents SDK in production?

Every tool execution, from listbotinteractionlogs to searchbotsources, is automatically logged and visible inside your OpenAI developer dashboard. This gives you complete visibility into which tools your agents run.

Give your production OpenAI Agents SDK system direct access to your DocsBot knowledge bases with strict runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocsBot MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate DocsBot queries at runtime

This MCP Server lets you validate DocsBot queries at runtime before execution. Production environments can't tolerate raw, unchecked agent behaviors, so checking boundaries with `get_bot_details` is a must. You get clean tracing inside the OpenAI developer dashboard for every call to `ask_bot_question`. This lets you see exactly which knowledge source triggered an answer without guessing.

Coordinate specialized agents for documentation lookup

Your agent can coordinate specialized bots using `list_docsbot_teams` and `list_team_bots` to segment technical support queries. You can set up a triage agent that uses this MCP connection to find the exact team bot trained on the right documents. Once found, it hands the conversation off to a specialized support agent. This multi-agent handoff pattern prevents your primary agent from getting bogged down.

Audit bot knowledge bases at runtime using the MCP Server

Monitoring the health of your knowledge base starts with `get_bot_knowledge_summary` and `list_recently_indexed_bots`. Keep tabs on what your agents are reading before routing a customer question. If things look outdated, the agent can call `list_recently_indexed_bots` to check if a recent sync occurred. This prevents stale documentation from polluting your production support channels.

Setup guide

Set up DocsBot 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 DocsBot tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents`. Next, initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint, and pass it to your Agent constructor inside the `mcp_servers` list. Set `cacheToolsList=True` to keep your production runs fast.

Yes, you can design a supervisor agent that calls `list_team_bots` to locate the right bot for a specific user query. Once the supervisor identifies the correct bot, it passes the context to a specialized agent that executes `ask_bot_question`.

Every tool execution, from `list_bot_interaction_logs` to `search_bot_sources`, is automatically logged and visible inside your OpenAI developer dashboard. This gives you complete visibility into which tools your agents run.

This usually happens when the HTTP transport isn't configured correctly. Make sure your Vinkius endpoint URL is correct and that your async context manager is active before the agent tries to discover tools like `get_docsbot_account_metadata`.

All communication between your OpenAI Agents SDK and the Vinkius sandbox is isolated in ephemeral V8 containers. Your raw interaction logs and PDF sources remain encrypted and are only accessed via secure API tokens during tools execution.

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