How to Use the Forj MCP in OpenAI Agents SDK

Q: Can my OpenAI agent automatically approve Forj group requests?

Yes, if you design it that way. The agent can pull listpendingrequests and then execute addusertogroup based on rules you define in the prompt.

Build production-ready community management agents with the Forj MCP Server and 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 Forj MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe group administration with OpenAI Agents SDK

Managing Forj communities at scale means you need agents that don't accidentally wipe out your user base. By connecting the Forj MCP Server to your OpenAI agent, you can safely automate group creation. When your agent runs `create_group` or triggers `add_user_to_group`, OpenAI's built-in guardrails validate the action before execution. That prevents hallucinated group assignments. You can even set up specialized agents. One handles `list_pending_requests` while another reviews `get_user_activity`. The handoff between them is tracked natively in your OpenAI dashboard, so you always know exactly why a member was approved.

Discover members and trace activity logs

Finding the right Forj community member shouldn't require manual database queries. Your agent uses `find_user` to pull up exact matches by email, or `search_users` to scan your entire directory. Every tool call gets traced automatically. If a user reports an issue, your agent can instantly pull their history with `get_user_activity`. Because this runs through the OpenAI Agents SDK, you get full visibility into the agent's reasoning process as it correlates activity logs with `get_account_details`.

Audit your community infrastructure

Community infrastructure rots if you don't monitor your Forj setup. Your OpenAI agent can run routine checks on your configuration by calling `list_webhooks` to ensure external integrations are still firing correctly. It can also audit outbound invites using `list_invitations`. If a specific group has too many pending invites, the agent can cross-reference it with `get_group` and alert your human moderators. This keeps your community clean without manual oversight.

Setup guide

Set up Forj 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 Forj tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents via pip. Initialize the connection using MCPServerStreamableHttp with your Forj endpoint, then pass it in the mcp_servers array when building your Agent object.

Yes, if you design it that way. The agent can pull list_pending_requests and then execute add_user_to_group based on rules you define in the prompt.

The SDK gives you built-in tracing and specialized agent handoffs. Instead of writing complex logic to parse list_group_members, you just let the agent handle the tool execution natively.

Set cacheToolsList=True in your setup. This stops the agent from repeatedly asking the server for the tool schema during high-volume community management tasks.

Your agent accesses real community emails and activity logs via tools like find_user. Vinkius runs this MCP Server in an ephemeral V8 Isolate Sandbox, meaning those member details disappear the moment your OpenAI session ends.

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