Capacities MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Capacities through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Capacities Assistant",
instructions=(
"You help users interact with Capacities. "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Capacities"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Capacities MCP Server
Connect your Capacities account to any AI agent and take full control of your object-based personal knowledge management through natural conversation.
The OpenAI Agents SDK auto-discovers all 10 tools from Capacities through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Capacities, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Spaces & Structures — Enumerate your personal spaces and discover the exact object type structures mapping your active environment.
- Object Instantiation — Build new typed graph objects complying precisely with the predefined structure parameters.
- Daily Note Appends — Send quick thoughts, summaries, and Markdown text directly into your mapped daily note log.
- Content Lookups — Execute rapid keyword searches targeting explicit object hierarchies to track down active nodes.
- Rich Link Saving — Parse and inject web URLs dynamically into your space as Weblink objects, triggering automatic previews.
- Media & Tagging — Attach images and add tags to existing objects to organize your graph relations instantly.
The Capacities MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Capacities to OpenAI Agents SDK via MCP
Follow these steps to integrate the Capacities MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 10 tools from Capacities
Why Use OpenAI Agents SDK with the Capacities MCP Server
OpenAI Agents SDK provides unique advantages when paired with Capacities through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Capacities + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Capacities MCP Server delivers measurable value.
Automated workflows: build agents that query Capacities, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Capacities, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Capacities tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Capacities to resolve tickets, look up records, and update statuses without human intervention
Capacities MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Capacities to OpenAI Agents SDK via MCP:
add_tag
Add a structural categorical Tag linking explicitly dynamically grouping related Graph items via relations
create_object
Create a new typed object in a Capacities space bounded by specific graph rules instantiating entities
get_object
Retrieve a specific full explicit object by ID accessing its root graph data traversing properties internally
get_space_info
Retrieve detailed information about a Capacities space including all object types (structures), their property definitions, and configuration
get_structures
Get all object type definitions (structures) within a Capacities space exposing exact metadata parameters limitlessly
list_spaces
List all personal spaces in the Capacities account. Spaces are top-level containers for organizing objects, notes, and knowledge
lookup
Search for content across a specific Capacities space by title or explicit keywords tracking exact nodes
save_media
Locate and attach an explicit Media payload explicitly binding it directly onto existing specific record scopes
save_to_daily_note
Append strict Markdown textual payloads to the dynamically mapped daily note explicitly linking content blocks
save_weblink
Save a web URL as a Weblink object dynamically tracking automatic preview generation natively
Example Prompts for Capacities in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Capacities immediately.
"Search my 'Work' space for the product launch meeting notes and summarize them."
"Save this URL https://example.com to my 'Research' space as a new Weblink."
"Append the code I just wrote to my daily note to remember the bugfix."
Troubleshooting Capacities MCP Server with OpenAI Agents SDK
Common issues when connecting Capacities to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Capacities + OpenAI Agents SDK FAQ
Common questions about integrating Capacities MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Capacities with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Capacities to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.