2,500+ MCP servers ready to use
Vinkius

Poe MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Poe through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Vinkius supports streamable HTTP and SSE.

python
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Poe Assistant",
            instructions=(
                "You help users interact with Poe. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Poe"
        )
        print(result.final_output)

asyncio.run(main())
Poe
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Poe MCP Server

Connect your Poe (Quora's AI platform) account to any AI agent and manage your chatbot empire through natural conversation. Create bots, chain AI model responses, monitor conversations, and track performance — all via API.

The OpenAI Agents SDK auto-discovers all 10 tools from Poe through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Poe, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

  • Bot Management — List, create, update, and delete API bots programmatically
  • AI Model Chaining — Query any bot on Poe (GPT-4, Claude, etc.) from your bot using API v2
  • Message Monitoring — View recent conversations, debug responses, and analyze user interactions
  • Usage Statistics — Track message counts, unique users, response times, and error rates
  • Endpoint Testing — Send test messages to verify bot connectivity and response quality
  • Multi-Model Workflows — Build complex bots that combine responses from multiple AI models

The Poe MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Poe to OpenAI Agents SDK via MCP

Follow these steps to integrate the Poe MCP Server with OpenAI Agents SDK.

01

Install the SDK

Run pip install openai-agents in your Python environment

02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

03

Run the script

Save the code above and run it: python agent.py

04

Explore tools

The agent will automatically discover 10 tools from Poe

Why Use OpenAI Agents SDK with the Poe MCP Server

OpenAI Agents SDK provides unique advantages when paired with Poe through the Model Context Protocol.

01

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

02

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

03

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

04

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Poe + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Poe MCP Server delivers measurable value.

01

Automated workflows: build agents that query Poe, process the data, and trigger follow-up actions autonomously

02

Multi-agent orchestration: create specialist agents — one queries Poe, another analyzes results, a third generates reports

03

Data enrichment pipelines: stream data through Poe tools and transform it with OpenAI models in a single async loop

04

Customer support bots: agents query Poe to resolve tickets, look up records, and update statuses without human intervention

Poe MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Poe to OpenAI Agents SDK via MCP:

01

create_bot

Requires a bot name, base URL for your API endpoint, and the model name. Optionally set a system prompt and description. Create a new API bot on Poe

02

delete_bot

This action cannot be undone. All conversation history and settings for the bot will be lost. Delete a Poe API bot

03

get_bot

Use the bot ID obtained from list_bots. Get details of a specific Poe bot

04

get_bot_stats

Essential for monitoring bot health, understanding user engagement, and identifying performance bottlenecks. Get usage statistics for a Poe bot

05

list_available_bots

Useful for discovering which AI models and specialized bots are available for chaining in your bot workflows. List publicly available bots on Poe that your bot can query

06

list_bots

Returns bot names, handles, models, and status. Essential first step to identify which bot to work with before querying, updating, or checking stats. List all API bots under your Poe account

07

list_messages

Useful for monitoring what users are asking, debugging bot responses, and analyzing conversation patterns. Returns message content, timestamps, and user identifiers. List recent messages for a specific Poe bot

08

query_bot

This allows chaining bot responses - your bot can query GPT-4, Claude, or any other bot on Poe and use the response as input. The cost is covered by the user's free message limit or subscription. Query another bot on Poe from your bot

09

send_message

Useful for testing endpoint connectivity and validating bot responses. The bot will process the message and return a response via its configured endpoint. Send a message to a Poe bot (simulate user interaction)

10

update_bot

Changes take effect immediately for new conversations. Update an existing Poe bot's configuration

Example Prompts for Poe in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Poe immediately.

01

"List all my bots and show stats for the first one."

02

"Create a bot called 'Research Assistant' using GPT-4 that summarizes articles."

03

"Query Claude-3.5-Sonnet from my ResearchBot: 'What are the key trends in AI?'"

Troubleshooting Poe MCP Server with OpenAI Agents SDK

Common issues when connecting Poe to OpenAI Agents SDK through the Vinkius, and how to resolve them.

01

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents
02

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Poe + OpenAI Agents SDK FAQ

Common questions about integrating Poe MCP Server with OpenAI Agents SDK.

01

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
02

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
03

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with the Vinkius.

Connect Poe to OpenAI Agents SDK

Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.