How to Use the Capsulink MCP in AutoGen

Q: How do I hook up Capsulink to AutoGen?

Install autogen-extmcp. Use mcpservertools with your Vinkius Streamable HTTP URL, then pass the resulting list to your AssistantAgent.

Q: How do multiple AutoGen agents share Capsulink stats?

One agent fetches the data using getlinkstats. The JSON output drops into the shared conversation history, where other agents read and debate the numbers.

Q: Does the MCP Server require custom schemas for AutoGen?

No. The McpToolAdapter automatically translates the tool definitions into the format your agents expect.

Let your AutoGen agents debate, analyze, and execute Capsulink link strategies through consensus-driven tool calls.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capsulink MCP to AutoGen

Create your Vinkius account to connect Capsulink 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 Capsulink with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen debate for link editing

The `edit_link_destination` and `shorten_url` MCP tools become actionable outcomes of agent negotiation. A marketing agent proposes a new redirect, while an SEO agent verifies the destination before allowing the operation. Nothing changes in your account until the agents agree. They discuss the target URL, format the request, and execute the creation only when consensus is reached.

Collaborative click analysis

Multiple agents request data via the `get_link_daily_stats` and `get_link_stats` tools to evaluate campaign success. A data analyst agent pulls the numbers, and a strategist agent interprets the daily breakdown. They challenge each other's conclusions based on the raw metrics. If the analyst flags a drop in traffic, the strategist might suggest pivoting the ad spend.

Auditing the URL directory

Running `list_links` and `get_link_details` through this MCP Server gives an auditor agent the context needed to clean up old redirects. It scans the active URLs and proposes a deletion list. A manager agent reviews the proposed list before calling `delete_link`. This multi-perspective check prevents accidental removal of active marketing assets.

Setup guide

Set up Capsulink 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 Capsulink 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="Capsulink_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Capsulink 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="Capsulink_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Capsulink 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 Capsulink. 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 Capsulink 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 Capsulink MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with your Vinkius Streamable HTTP URL, then pass the resulting list to your `AssistantAgent`.

Yes. Once the agents agree on the destination, one of them calls `shorten_url` and returns the generated link to the chat.

One agent fetches the data using `get_link_stats`. The JSON output drops into the shared conversation history, where other agents read and debate the numbers.

No. The `McpToolAdapter` automatically translates the tool definitions into the format your agents expect.

The MCP Server processes target URLs, folder names, and click metrics. Vinkius isolates this execution in a temporary sandbox that spins down instantly, leaving no trace of the API response on the server.

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