How to Use the Flock MCP in OpenAI Agents SDK

Q: How does the Flock MCP server integrate with OpenAI Agents SDK guardrails?

You define validation hooks before executing tools like chatsendmessage. The SDK evaluates the agent's proposed FlockML payload against your safety policies before making the API call.

Q: How do I configure the Flock MCP connection in OpenAI Agents SDK?

Install the SDK via pip and initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this server instance in the mcpservers list when creating your Agent.

Q: How does the agent handle paginated chat history?

The agent uses chatfetchmessages to pull historical JSON payloads from a room. It reads these strings to understand conversation context before replying.

Spin up autonomous OpenAI Agents SDK workflows that manage Flock channels and route messages without manual intervention.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flock MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send formatted FlockML alerts using OpenAI Agents SDK

The `chat_send_message` tool lets your agent send rich enterprise alerts formatted in FlockML, bypassing standard Markdown limitations. This is critical when you need to render complex UI elements or structured tables directly inside a Flock chat room. Your agent uses this tool to format incident reports dynamically. It handles the raw payload delivery, so your team gets highly readable alerts in the channel the second an outage triggers.

Map team directories dynamically via MCP Server tools

The `roster_list_directory` tool maps user aliases to absolute UUID strings to resolve routing issues. Your agent queries this directory to find the right on-call engineer during an active incident. It combines this with `users_get_metadata` to check timezone and role before sending a message. This prevents your agent from waking up off-duty developers.

Audit private group access within agent handoffs

The `groups_list_private` tool returns the UUID arrays needed to locate secure, non-public channels within this MCP server. When your guardrails trigger an agent handoff, the new agent uses this tool to find the correct private room for escalation. It then runs `groups_get_info` to verify internal credentials before posting sensitive security logs. This ensures your data never leaks into public channels.

Setup guide

Set up Flock 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 Flock tools at runtime.
3

Create your Agent

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

Run the agent

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

You define validation hooks before executing tools like `chat_send_message`. The SDK evaluates the agent's proposed FlockML payload against your safety policies before making the API call.

Yes, you can route tasks between specialized agents. For example, a triage agent uses `roster_list_directory` to find a user, then hands off the context to a messaging agent to execute `chat_send_message`.

Install the SDK via pip and initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this server instance in the `mcp_servers` list when creating your Agent.

The agent uses `chat_fetch_messages` to pull historical JSON payloads from a room. It reads these strings to understand conversation context before replying.

Yes. All data, including channel membership UUIDs and Flock chat messages, runs inside an isolated V8 sandbox on Vinkius. No credentials or raw payloads are stored on our servers.

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