How to Use the AutoGen MCP in Claude Code

Q: How do I add the AutoGen MCP server to Claude Code?

Type claude mcp add --transport http autogen-mcp -- in your terminal. Make sure you pass the transport flag before the server name. Use the list command afterward to confirm the tools registered.

Control your multi-agent pipelines from the terminal. Claude Code manages AutoGen configurations directly via the command line.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AutoGen MCP to Claude Code

Create your Vinkius account to connect AutoGen to Claude Code 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 AutoGen with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script your AutoGen deployments

Provisioning agent swarms via GUI is a waste of time for backend engineers. You can pipe a configuration file straight into your terminal, and the MCP Server uses `create_agent` to spin up the required roles. Everything happens headlessly without a single browser window. Auditing your current setup takes exactly one command. The CLI client hits `list_agents` and `list_workflows` to dump your active topology into standard output. From there, you can grep the results or feed them into another step in your CI/CD pipeline.

Run headless chat sessions

Automated testing for AI pipelines requires a completely programmatic approach. Your terminal assistant kicks off a fresh environment using `create_session` and injects test payloads via `create_message`. No manual clicking required. Pulling the execution logs is just as straightforward. The tool runs `list_messages` to grab the raw transcript and can append it to a log file for review. When the cron job finishes, `delete_session` wipes the slate clean for the next run.

Audit AutoGen skills via MCP Server

Keeping track of which Python functions your bots can execute gets messy at scale. A quick terminal command tells the AI to run `list_skills`, giving you an instant inventory of available tools. You know exactly what your swarm is capable of doing. Checking model configurations works the exact same way. The system queries `list_models` to verify your endpoints are correctly mapped before a massive job starts. Catching a misconfigured API route before deployment saves hours of debugging later.

Setup guide

Set up AutoGen MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see autogen-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest AutoGen transactions." It will automatically discover and invoke the available AutoGen tools.

Terminal

claude mcp add --transport http autogen-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the AutoGen MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "autogen-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Microsoft AutoGen. 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 AutoGen 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 AutoGen MCP in Claude Code

Type `claude mcp add --transport http autogen-mcp -- ` in your terminal. Make sure you pass the transport flag before the server name. Use the list command afterward to confirm the tools registered.

Yes, this setup is perfect for CI/CD pipelines. You can write a shell script that tells the CLI assistant to spin up a session, run a test conversation, and report the results back to your pull request.

It treats them like standard text streams. The assistant fetches the message arrays and formats them for your terminal, meaning you can pipe the output into `jq`, save it to a file, or pass it to another CLI tool.

The process takes seconds. You just tell your terminal assistant to clear out the garbage, and it iterates through the active IDs, nuking them one by one.

Not a chance. Your workflow definitions, raw message payloads, and Python skill scripts live inside an isolated V8 sandbox during execution. Once the HTTP request resolves, the ephemeral container vanishes along with your data.

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