How to Use the Capacities MCP in AutoGen

Q: Can AutoGen agents manage multiple Capacities spaces?

Yes, a coordinator agent can run listspaces to identify target spaces. It then assigns specific spaces to different sub-agents based on their designated roles.

Q: How do AutoGen agents handle files in Capacities?

An agent can download a file and use savemedia to attach it to a specific node. The agents can then discuss the contents of the attachment and update the node's properties accordingly.

Let your AutoGen agents debate, organize, and write structured notes directly into your Capacities graph using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capacities MCP to AutoGen

Create your Vinkius account to connect Capacities 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 Capacities with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents collaborate on graph creation

The `create_object` tool allows your writing agent to draft new structured nodes inside your workspace via the MCP Server. Before publishing, a separate editor agent can inspect the draft node and approve its properties. Once the agents reach a consensus, they run `add_tag` to categorize the node. This multi-agent review process ensures only high-quality, pre-vetted information enters your personal wiki.

Cross-reference workspace nodes during agent debates

The `get_object` tool gives your debating agents access to the exact properties of any node. If one agent makes a claim, another agent can pull the node's data to verify the facts. To resolve disagreements about where to link a node, the agents use `get_structures` to check the valid relationships of your workspace. They negotiate the best structural placement based on your existing rules.

Log multi-agent session histories automatically

The `save_to_daily_note` tool lets your coordinator agent append the final transcript of an agent debate to your daily log. This keeps a permanent record of the decisions your agents made throughout the day. If the debate involved external research, the agents run `save_weblink` to store the source URLs. This links the discussion directly to the raw evidence inside your graph over a secure MCP connection.

Setup guide

Set up Capacities 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 Capacities 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="Capacities_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the autogen-ext package to fetch the tools from your Vinkius endpoint using StreamableHttpServerParams to initialize the MCP adapter. Pass the resulting tool list directly to your AssistantAgent constructor.

Yes, a coordinator agent can run `list_spaces` to identify target spaces. It then assigns specific spaces to different sub-agents based on their designated roles.

An agent can download a file and use `save_media` to attach it to a specific node. The agents can then discuss the contents of the attachment and update the node's properties accordingly.

The server handles requests sequentially. If a conflict occurs, the agents can run `get_object` to fetch the latest state, resolve the conflict through conversation, and write the final version.

Yes, Vinkius runs the server in an isolated V8 sandbox. This prevents any agent from executing unauthorized system commands or accessing your raw database schema outside your specified spaces.

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