How to Use the Craft.io MCP in AutoGen

Q: How do I assign specific Craft.io tools to different AutoGen agents?

When you create an AssistantAgent, you pass a list of tools to its llmconfig. To give an agent specific tools, just filter the list from mcpservertools and provide only the ones you want that agent to have access to.

Q: Can I have an AutoGen agent that only reads from Craft.io and another that writes?

Yes. Create a 'Reader' agent and only give it the 'get' and 'list' tools. Create a 'Writer' agent and give it the createitem tool. This is a great way to enforce separation of concerns in your agent group.

Q: What's a simple multi-agent setup for Craft.io and AutoGen?

Start with two agents. One AssistantAgent with all the Craft.io tools, and one UserProxyAgent to represent you. You can give the assistant a task, and it will use the tools and report back, asking for clarification if needed.

Assemble teams of AutoGen agents to debate product strategy and update your Craft.io roadmaps.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Craft.io MCP to AutoGen

Create your Vinkius account to connect Craft.io 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 Craft.io with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run a Multi-Agent Strategy Session

Model your product team with agents. Create a 'Product Manager' agent that uses `list_items` and `get_item` to track the current roadmap. Assign a 'Market Analyst' agent to monitor the competition using `search_companies` and `get_company_competitors`. Then, let them talk. The Analyst agent can report a new competitor launch, and the Product Manager agent can check the backlog for relevant features. They'll debate priority and suggest actions, using live data from your Craft.io instance to back up their arguments.

Let Agents Debate and Create Tasks

This isn't just a discussion group. Once your agents reach a consensus, a 'Planner' agent can execute the decision. It can take the outcome of the debate and use the `create_item` tool to add a new task directly to your Craft.io product backlog. With this MCP Server, the entire loop is automated. The process goes from market discovery with `get_company_news`, to team debate, to task creation with `create_item`, all handled by the conversation between your AutoGen agents. You just define the team and the goal.

An AutoGen Team for Product Management

Build specialized agents that mirror real-world roles. A 'Finance' agent could have exclusive access to the `get_company_financials` tool to weigh in on budget. A 'QA' agent could use `get_item` to report on the status of features currently in testing. AutoGen lets you build systems that deliberate. One agent proposes an idea, another challenges its cost, and a third confirms the technical details by calling a tool. This MCP connection to Craft.io gives your agent team the ground truth they need to have a productive debate.

Setup guide

Set up Craft.io 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 Craft.io 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="Craft.io_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

When you create an `AssistantAgent`, you pass a list of tools to its `llm_config`. To give an agent specific tools, just filter the list from `mcp_server_tools` and provide only the ones you want that agent to have access to.

Yes. Create a 'Reader' agent and only give it the 'get_*' and 'list_*' tools. Create a 'Writer' agent and give it the `create_item` tool. This is a great way to enforce separation of concerns in your agent group.

Start with two agents. One `AssistantAgent` with all the Craft.io tools, and one `UserProxyAgent` to represent you. You can give the assistant a task, and it will use the tools and report back, asking for clarification if needed.

The conversation is printed to your console by default. You'll see which agent is speaking, what they're saying, and which tool they're calling with which arguments. The `McpToolAdapter` handles the tool call execution in the background.

The conversation, including any workspace items or portfolio data returned by tools, lives within your running AutoGen application. The tool calls themselves are proxied through Vinkius, where each request is processed in a zero-trust, sandboxed V8 isolate that is torn down immediately after.

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