How to Use the LinkAce MCP in OpenAI Agents SDK

Q: Can my agent create tags automatically using LinkAce and OpenAI Agents SDK?

Yes, your agent can discover the createnewtag tool at runtime. It can check for existing tags using listalltags before creating a new one.

Q: What tools does this integration expose to my agent?

It exposes nine tools including createnewbookmark, deletebookmark, and searchbookmarks. Your agent reads these tool definitions directly from the MCP Server schema.

Deploy production-ready OpenAI Agents SDK workflows that manage, tag, and search your LinkAce bookmark collections automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LinkAce MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Archive and tag URLs with OpenAI Agents SDK

The `create_new_bookmark` tool writes links straight to your LinkAce database. Your agent intercepts incoming URLs, processes them, and categorizes them using `create_new_tag` to keep things organized. This MCP server runs inside an isolated sandbox to protect your credentials. You can configure OpenAI Agents SDK guardrails in Python to check the payload before the agent executes the write.

Search and inspect links inside agent runs

The `search_bookmarks` tool queries your entire LinkAce library using simple keywords. When it finds a match, it grabs metadata using `get_bookmark_details` to verify the link is actually what you wanted. This setup hooks right into OpenAI's tracing dashboard so you can watch exactly what your agent searched. The agent auto-discovers these tools, meaning you don't have to manually map endpoints in your schema.

Manage collections with safe agent handoffs

The `create_new_collection` tool lets your agent group related links into structured folders. If you run multiple specialized agents, one can grab links while another organizes them using `list_all_collections` to avoid duplicates. Using this MCP Server ensures that your production pipelines remain stable. You can use the `list_all_bookmarks` tool to sync states between different runs without exposing raw LinkAce API credentials to the runtime.

Setup guide

Set up LinkAce 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 LinkAce tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK via pip, then initialize the server streamable HTTP class with your Vinkius endpoint. Pass this server instance inside the agent constructor's server list.

Yes, your agent can discover the `create_new_tag` tool at runtime. It can check for existing tags using `list_all_tags` before creating a new one.

Set the cache tools list parameter to true in your configuration to avoid redundant schema lookups. For heavy write operations, implement backoff logic in your Python runner.

It exposes nine tools including `create_new_bookmark`, `delete_bookmark`, and `search_bookmarks`. Your agent reads these tool definitions directly from the MCP Server schema.

Your LinkAce API token is stored securely within the Vinkius vault and never exposed to the agent or external networks. The server only transmits the bookmark URLs and tag names required to execute your specific tool calls.

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