How to Use the Keepcon MCP in OpenAI Agents SDK

Q: Does the server support fetching multiple users at once?

You pull bulk user data using the listprofiles tool. It returns an array of existing user records based on your pagination parameters.

Build production-ready moderation agents with Keepcon and the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keepcon MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time moderation and feedback loops.

The Keepcon MCP Server lets your OpenAI agents intercept and evaluate user submissions instantly. Using the `moderate_content` tool, the agent passes text to the semantic engine and receives an immediate approve or reject decision alongside categorical tags. You are building a production system, which means handling edge cases matters. If an agent spots a false positive, it triggers `submit_feedback` to correct the platform baseline logic. Your moderation pipeline actually gets smarter over time without requiring manual rule adjustments.

Batch processing at scale.

High-volume customer support queues require async processing. Your agent groups thousands of comments and triggers `import_batch` to send them off for background analysis. Once the semantic engine finishes the workload, the agent runs `export_results` to pull the verdicts down. It then clears the queue by firing `acknowledge_results`. You can trace this entire multi-step workflow straight from your OpenAI dashboard.

Cross-network profile tracking.

Support teams need context on who is posting. The agent uses `get_profile_by_social_id` to map a Twitter or Facebook handle directly to a known Keepcon user profile. If a user tries evading bans with alt accounts, the agent calls `search_profiles` with specific filters to find matching behavior patterns. OpenAI built-in guardrails ensure the agent only queries profiles when a moderation flag is active, keeping your data access compliant.

Setup guide

Set up Keepcon 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 Keepcon tools at runtime.
3

Create your Agent

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

Run the agent

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

Initialize MCPServerStreamableHttp with your endpoint URL. Pass it into the mcp_servers list when instantiating your Agent. Set cacheToolsList=True to speed up the initial tool discovery phase.

Yes. You configure an OpenAI agent to handle the initial text check. If the returned tags indicate high severity, the SDK handoff mechanism routes the ticket to a specialized human-in-the-loop agent.

You pull bulk user data using the `list_profiles` tool. It returns an array of existing user records based on your pagination parameters.

Check your OpenAI tracing logs. The agent must receive an import ID from `import_batch` before it attempts to pull data with `export_results`.

The server acts as a strict conduit between your AI client and the Keepcon API. Text payloads and social network IDs sent through `moderate_content` or `get_profile_by_social_id` process in memory within the V8 Isolate Sandbox. The ephemeral environment destroys the context immediately after the HTTP response resolves.

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