Can my agent send formatted messages using FlockML?

Yes. Use the 'chat_send_message' tool and provide your XML string in the 'flockml' parameter. The agent will bypass standard Markdown limits to render rich enterprise attachments and layouts natively in Flock.

How do I list all members of a specific private group via chat?

Use the 'groups_list_members' tool. Provide the Group UUID. Your agent will surface the explicitly mapped profiles within that group, helping you verify sensitive message targets securely.

Can I search for a user's UUID using their '@' alias through the agent?

Absolutely. The 'roster_list_directory' tool discovers global identity blocks mapping direct aliases to absolute string UUIDs, ensuring you can route messages accurately to anyone in your company.

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

Name: Flock
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

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

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

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

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

asyncio.run(main())

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 Flock MCP Server

Connect your Flock bot to any AI agent and take full control of your team communication, private groups, and organizational roster through natural conversation.

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

What you can do

Rich Messaging Orchestration — Provision massively fast payloads strictly into Flock chats, utilizing ` to render rich enterprise attachments and formatted layouts natively


Public Channel Discovery — Enumerate explicitly attached public channels and execute bulk iterations to capture global namespaces and routing configurations synchronously
Private Group Management — Identify bounded private groups and retrieve precise physical definitions detailing exactly how hidden groups operate within your enterprise

Organizational Roster Auditing — Discovers global identity blocks mapping direct @` aliases to absolute string UUIDs to solve accurate routing for the entire company
Identity Metadata Retrieval — Perform structural extraction of profile metadata linked to Flock users, resolving time zones and LDAP/SSO properties securely
Chat Log Ingestion — Pull chronological asynchronous logs from any room, extracting raw JSON objects mapping historical strings natively from chat fetchers
Membership Oversight — Audit IAM boundaries and identify explicit active UUIDs directly attached to channels or groups to verify intended audiences flawlessly

The Flock 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 Flock to OpenAI Agents SDK via MCP

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

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

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

Run the script

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

Explore tools

The agent will automatically discover 10 tools from Flock

Why Use OpenAI Agents SDK with the Flock MCP Server

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

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

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

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

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

Flock + OpenAI Agents SDK Use Cases

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

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

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

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

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

Flock MCP Tools for OpenAI Agents SDK (10)

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

channels_get_info

Retrieve explicit Channel descriptions and banner logic mappings

channels_list_members

Identify explicit Active UUIDs directly attached evaluating Channel ingress

channels_list_public

Enumerate explicitly attached `public` channels active within Flock

chat_fetch_messages

Extracts raw JSON objects mapping historical strings natively returned by `chat.fetchMessages`. Read recent structural Chat payloads targeting a Flock Room

chat_send_message

Detects if formatted `<flockml>` definitions are passed and converts the payload dynamically bypassing standard Markdown limits rendering rich enterprise attachments. Provision a massively fast payload strictly into an established Flock Chat

groups_get_info

Inspect deep internal credentials identifying a precise Private Group

groups_list_members

Crucial for verifying sensitive message targets. Audit IAM boundaries explicitly granting read permissions to a Group

groups_list_private

Returns arrays necessary to retrieve correct routing UUIDs. Identify bounded Private Groups tracking strict IAM boundaries

roster_list_directory

Returns explicit array definitions mapping direct `@` aliases to absolute string UUIDs solving accurate routing natively. Identify precise active Human constraints navigating the entire Flock company

users_get_metadata

Perform structural extraction of metadata linked to a Flock Identity

Example Prompts for Flock in OpenAI Agents SDK

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

"Send a message to group 'g:123': 'Project update is live!'"

"List all public channels in my Flock workspace"

"Get the metadata for user '@john_doe'"

Troubleshooting Flock MCP Server with OpenAI Agents SDK

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

MCPServerStreamableHttp not found

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

Agent not calling tools

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

Flock + OpenAI Agents SDK FAQ

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

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.