How to Use the Cosmic MCP in AutoGen

Q: How do I register Cosmic tools with AutoGen?

Use the mcpservertools adapter to fetch the tools from your Vinkius endpoint. You can then pass this tool list directly to your AutoGen AssistantAgent.

Let your AutoGen agents debate and collaborate on Cosmic content drafts and schema updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cosmic MCP to AutoGen

Create your Vinkius account to connect Cosmic 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 Cosmic with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative draft editing with AutoGen

One agent can run `get_single_object` to inspect a draft, while a reviewer agent checks the values against schema rules from `get_schema_details`. They debate the changes before a third agent applies the update using `patch_cms_object`. This multi-agent workflow ensures no draft gets updated without meeting your editorial standards. The entire conversation happens autonomously before any write operation hits your live bucket.

Multi-agent schema auditing via MCP Server

Deploy a specialized auditor agent that runs `list_schema_types` to check for structural changes. If it finds a discrepancy, it alerts the editor agent to pause `create_cms_object` calls until the schema matches. This consensus-driven approach prevents broken database writes. Your agents negotiate the correct field mappings in real-time, adapting to schema shifts without human intervention.

Safe asset deprecation through agent consensus

Before running destructive tools like `wipe_media_asset` or `wipe_cms_object`, your agents can cross-reference active files using `list_uploaded_media` and `list_bucket_objects`. A safety agent can veto the deletion if the asset ID is still referenced in an active draft, ensuring you never accidentally delete live website images.

Setup guide

Set up Cosmic 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 Cosmic 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="Cosmic_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the mcp_server_tools adapter to fetch the tools from your Vinkius endpoint. You can then pass this tool list directly to your AutoGen AssistantAgent.

Yes. The MCP Server handles concurrent requests, allowing your editorial and audit agents to fetch schema details and list media at the same time.

They debate the proposed edits in their chat history. Once they agree on the payload, the executor agent calls `patch_cms_object` to apply the consensus decision.

Yes. You can configure your agent roles so only a designated administrator agent has access to destructive tools like `wipe_cms_object`.

All tool executions run inside an isolated Vinkius sandbox. Your draft payloads and media assets are processed on ephemeral instances, meaning no persistent data is left behind after the agents finish their debate.

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