How to Use the LinkAce MCP in AutoGen

Q: Can AutoGen agents collaborate to clean up dead LinkAce bookmarks?

Yes, one agent can fetch bookmarks using listallbookmarks and test the URLs. A second agent can verify the results and instruct a third agent to call deletebookmark.

Let your AutoGen agents debate, organize, and curate 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 AutoGen

Create your Vinkius account to connect LinkAce to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent curation with AutoGen and LinkAce

This MCP Server enables cooperative curation by letting one agent find links with `list_all_bookmarks` while another evaluates their quality. The agents discuss whether a bookmark is still relevant before making changes. If they agree a link is dead, a third agent can execute `delete_bookmark` to keep your archive clean. This consensus-driven approach prevents accidental deletions and ensures your library stays highly curated.

Collaborative tagging and organization

The `list_all_tags` tool provides your agent team with the current taxonomy of your LinkAce account. A categorization agent can suggest new tags, while a security agent checks them for consistency. Once they reach an agreement, the team uses `create_new_tag` to register the new labels. This ensures your bookmarks are organized under a clean, pre-approved system without human intervention.

Automated collection management via agent debate

The `list_all_collections` tool allows your agents to inspect your existing folder structure. They can debate whether a newly saved link belongs in an existing folder or if a new one is required. If they decide a new folder is needed, they call `create_new_collection` to set it up. This keeps your web research organized dynamically as your agents compile resources.

Setup guide

Set up LinkAce MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes LinkAce tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="LinkAce_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent LinkAce data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="LinkAce_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent LinkAce data")
    print(result.messages[-1].content)

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 AutoGen

Install autogen-ext and use the MCP adapter to load the tools. Pass the resulting tool list to your AssistantAgent configuration so your agents can start calling them.

Yes, one agent can fetch bookmarks using `list_all_bookmarks` and test the URLs. A second agent can verify the results and instruct a third agent to call `delete_bookmark`.

They resolve conflicts through multi-agent chat. If two agents suggest different tags, they debate the options and use `create_new_tag` only after reaching a consensus.

Yes, the client supports Streamable HTTP transport. You can connect your AutoGen agents to the hosted Vinkius endpoint using your unique MCP access token.

Your LinkAce API token is stored as an environment variable inside an ephemeral, zero-trust MCP sandbox. This prevents other agents or external scripts from ever accessing your credentials.

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