How to Use the BlogIn MCP in OpenAI Agents SDK

Q: How do I connect BlogIn to my OpenAI Agents SDK pipeline?

Install the package using pip install openai-agents in your environment. Initialize the server using MCPServerStreamableHttp with your Vinkius endpoint. Pass this MCP instance into your Agent constructor's mcpservers list to start calling tools.

Q: Can the OpenAI Agents SDK cache the BlogIn tool list?

Yes, you set cacheToolsList=True during initialization. This prevents redundant network requests for schema definitions. Your agent starts up faster and saves on API latency.

Q: How do I list posts using this setup?

Your agent automatically calls listposts when asked for recent company announcements. It parses the JSON payload and presents the summaries directly in your chat interface.

Draft, edit, and read team updates directly within your OpenAI Agents SDK production MCP workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BlogIn MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Publish updates directly using this MCP Server

This BlogIn MCP Server connects your OpenAI agent to your internal company wiki and blog posts. Your Python agent calls `create_internal_post` to draft and publish team updates without leaving your terminal. You configure the agent with guardrails so it never publishes drafts before a human reviews them. The agent reads category structures with `list_categories` to file the new post correctly.

Monitor internal feedback loops automatically

The `list_recent_comments` tool pulls the latest discussions from your company blog into your agent's context window. This lets your system flag negative sentiment or unanswered questions instantly. Your agent uses `get_post_details` to pull the full body of flagged posts. OpenAI's tracing dashboard tracks every single tool call to keep your pipeline transparent.

Map your organizational knowledge graph

The `list_internal_pages` tool exposes your entire company directory and wiki structure to your autonomous system. This gives your agent the exact layout of your internal documentation. It matches posts to authors using `list_team_members` to build an accurate index of who knows what. Your agent routes questions to the right subject matter experts using this live map.

Setup guide

Set up BlogIn 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 BlogIn tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents` in your environment. Initialize the server using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this MCP instance into your Agent constructor's `mcp_servers` list to start calling tools.

Yes, you set `cacheToolsList=True` during initialization. This prevents redundant network requests for schema definitions. Your agent starts up faster and saves on API latency.

Absolutely. You can route a user query from a triage agent to a dedicated writer agent that holds the `create_internal_post` tool. The SDK handles the transition and maintains the conversation state.

Your agent automatically calls `list_posts` when asked for recent company announcements. It parses the JSON payload and presents the summaries directly in your chat interface.

Your internal blog posts, team lists, and comments remain isolated within Vinkius's secure V8 sandboxes. No data is cached or stored on our servers. Every request uses temporary credentials that expire immediately after the tool execution completes.

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