How to Use the Discourse MCP in OpenAI Agents SDK

Q: How does OpenAI Agents SDK search Discourse content?

The agent uses the searchcommunitycontent tool to query your forum. You just pass a keyword, and the MCP server returns the relevant threads to your OpenAI Agents SDK workflow.

Q: Can OpenAI Agents SDK monitor Discourse trending topics?

Yes. The agent calls listtrendingdiscussions to identify high-engagement threads. It then analyzes those posts to determine if your intervention is required.

Q: How do I list groups in Discourse using OpenAI Agents SDK?

You call listcommunitygroups to get a list of all groups. If you need specific members, pass the group name to listgroupmembers for a full breakdown.

Bring your OpenAI Agents SDK production systems directly into your forum data with this Discourse MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Discourse MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time thread monitoring for OpenAI Agents SDK

Your agent tracks active discussions by calling `list_latest_topics`. It pulls the data directly from your instance to keep your agents informed of current events. Once a relevant thread appears, the agent uses `get_topic_details` to read the full conversation. This keeps your production system reacting to real user input without manual intervention.

Manage community profiles via MCP Server

You can now query user stats using `get_user_profile` within your agent pipeline. It pulls exact account details so your logic makes decisions based on real member history. This MCP Server provides clean data structures for your agents. You avoid parsing raw API responses and get ready-to-use objects for your safety guardrails.

Automated content discovery for agents

Search your entire forum database using `search_community_content` to find specific keywords or user mentions. Your agent runs these queries to build context for its next move. It connects to your Discourse instance to filter through categories via `list_forum_categories`. Your agent stays focused on the right sub-forums without scanning irrelevant noise.

Setup guide

Set up Discourse 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 Discourse tools at runtime.
3

Create your Agent

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

Run the agent

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

The agent uses the `search_community_content` tool to query your forum. You just pass a keyword, and the MCP server returns the relevant threads to your OpenAI Agents SDK workflow.

Yes. The agent calls `list_trending_discussions` to identify high-engagement threads. It then analyzes those posts to determine if your intervention is required.

Vinkius handles the transport security for your Discourse integration. Your OpenAI Agents SDK instance only receives the specific data returned by the tools you explicitly allow.

You call `list_community_groups` to get a list of all groups. If you need specific members, pass the group name to `list_group_members` for a full breakdown.

The server respects the permissions tied to your API key. If your Discourse key has access to private categories, the tools will retrieve that information for your agent.

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