Can it apply Supertags with pre-filled fields?

Yes. Use `add_node_with_fields` to create a node with a specific Supertag and populate its attributes in a single call.

Are there limits on nested hierarchies?

No practical limits beyond your token window. The `add_node_with_children` tool accepts arrays of child nodes and populates the hierarchy in a single request.

Which Tana plan is required?

API access is available on Tana Plus and Pro plans. Free accounts do not have API tokens. Generate your token from Workspace Settings in the Tana web app.

Tana MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Tana
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Tana through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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="Tana Assistant",
            instructions=(
                "You help users interact with Tana. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Tana"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Tana MCP Server

Translate your AI conversation into structured personal knowledge management seamlessly with the Tana MCP connector. Evolve your LLM into a dedicated ontological architect capable of pushing rich, contextual data fragments straight into your workspace. Bypass tedious manual entry by programming your assistant to dynamically categorize thoughts, mint native ontological classes (Supertags), and instantiate multi-level hierarchies inside your Tana graph while maintaining maximum focus in your local environment.

The OpenAI Agents SDK auto-discovers all 10 tools from Tana through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Tana, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Node Structuring — Swiftly inject clean data fragments anywhere by defining paths invoking add_node or securely drop ideations asynchronously into your capture zone utilizing add_to_inbox.
Ontology & Metadata — Formalize data classifications mapping real-world objects using define_supertag and instantiate them powerfully utilizing add_tagged_node and add_node_with_fields.
Hierarchy & Linking — Push whole outline structures programmatically executing add_node_with_children and enforce complex bi-directional network paths executing add_node_reference.
Specialized Datatypes — Effortlessly instantiate formatted daily operations leveraging add_checkbox_task, temporal entries mapping add_date_node, or external resources resolving via add_url_bookmark.

The Tana 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 Tana to OpenAI Agents SDK via MCP

Follow these steps to integrate the Tana 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 Tana

Why Use OpenAI Agents SDK with the Tana MCP Server

OpenAI Agents SDK provides unique advantages when paired with Tana 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

Tana + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Tana MCP Server delivers measurable value.

Automated workflows: build agents that query Tana, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Tana, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Tana tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Tana to resolve tickets, look up records, and update statuses without human intervention

Tana MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Tana to OpenAI Agents SDK via MCP:

add_checkbox_task

Optionally set initial done status. Creates a checkbox/todo item in the Tana inbox

add_date_node

Format: YYYY-MM-DD. Creates a date-typed node in the Tana inbox

add_node

Provide a target node ID (or "INBOX", "LIBRARY") and the node name. Creates a new node in a specific Tana location

add_node_reference

Provide a label and the target node ID. Creates a reference node linking to an existing node

add_node_with_children

Provide a name and comma-separated children. Creates a parent node with multiple child nodes

add_node_with_fields

Provide name, supertag ID, and field data as a JSON object. Creates a supertagged node with structured field values

add_tagged_node

g. #meeting, #person). Requires the supertag ID from Tana schema. Creates a new node with a supertag applied

add_to_inbox

Quickly adds a new node directly to the Tana Inbox

add_url_bookmark

Creates a URL-typed node in Tana

define_supertag

Provide a name and description. Defines a new supertag in the Tana schema

Example Prompts for Tana in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Tana immediately.

"Add a new conceptual outline to my Inbox. The main title should be 'Quarterly Product Strategy', and it should contain three specific child nodes functioning as checkable tasks."

"Create a new node 'Meeting Notes format' structured in our weekly workspace."

"Search my Tana knowledge base for nodes tagged with '#project'."

Troubleshooting Tana MCP Server with OpenAI Agents SDK

Common issues when connecting Tana to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Tana + OpenAI Agents SDK FAQ

Common questions about integrating Tana MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.