How to Use the Capacities MCP in OpenAI Agents SDK

Q: How do I perform a Capacities search with OpenAI Agents SDK?

Use the lookup tool within your agent definition. It scans your space for titles or keywords, returning the relevant node IDs for further processing.

Q: Can OpenAI Agents SDK use Capacities for state tracking?

Yes, you can use createobject to store agent state as persistent entities. This keeps your agent's history inside your personal knowledge graph.

Build structured knowledge graphs in Capacities using your OpenAI Agents SDK production pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capacities MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject knowledge directly into Capacities

Use `create_object` and `save_weblink` to populate your graph based on agent findings. Your production agents move data from external sources into your specific spaces without manual copy-pasting. This MCP Server handles the schema mapping, ensuring your agent logic triggers the right object creation. You'll see your knowledge base grow as your agents finish their tasks.

Manage daily records through your SDK

Call `save_to_daily_note` to append agent findings to your current daily log. It keeps your research context inside Capacities while your agent runs in the background. Your SDK code stays clean because the server manages the connection overhead. You just pass the text payload and the server handles the rest.

Query your graph structures via agents

Run `get_structures` and `get_object` to let your agents reason about existing data. They read your property definitions before creating new entries, which prevents schema drift. This setup allows agents to adapt to your space configuration dynamically. They fetch the latest metadata before attempting to link new records.

Setup guide

Set up Capacities 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 Capacities tools at runtime.
3

Create your Agent

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

Run the agent

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

Use the `lookup` tool within your agent definition. It scans your space for titles or keywords, returning the relevant node IDs for further processing.

Yes, you can use `create_object` to store agent state as persistent entities. This keeps your agent's history inside your personal knowledge graph.

It integrates as a standard toolset. The server maps your agent requests to specific API calls, keeping your logic isolated from the transport layer.

The server only touches the specific space data you authorize. It acts as a bridge, reading or writing only when your agent invokes a tool.

Your notes remain within your account. The server transmits raw text payloads only during active tool execution and does not store your content on our infrastructure.

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