How to Use the Mealie (Recipe Manager) MCP in AutoGen

Q: How do I import Mealie (Recipe Manager) MCP Server tools into AutoGen?

Install autogen-extmcp and use mcpservertools with StreamableHttpServerParams pointing to your Vinkius server. Pass the resulting tool list to your AssistantAgent.

Q: Can AutoGen agents delete meal plans in Mealie (Recipe Manager)?

Yes, they can use deletemealplan. You can set up a supervisor agent in your AutoGen group to review and approve all deletion calls before they hit your database.

Q: How do agents coordinate shopping lists in Mealie (Recipe Manager) with AutoGen?

One agent reads active lists using listshoppinglists, while another processes the menu. They negotiate the changes and use toggleshoppinglistitem to update the state.

Q: Can I use this to categorize my recipes?

Yes. Your agents can query your setup using listcategories and listtags, then apply the correct metadata to new recipes using updaterecipe.

Let AutoGen agents debate meal plans, coordinate shopping lists, and manage your Mealie recipes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mealie (Recipe Manager) MCP to AutoGen

Create your Vinkius account to connect Mealie (Recipe Manager) 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 Mealie (Recipe Manager) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven meal planning with AutoGen

`create_meal_plan` is executed only after your AutoGen agents agree on the weekly menu. By adding this MCP Server to your group, a nutritionist agent can suggest meals while a budget agent reviews ingredient costs. Once they reach a consensus, the primary execution agent calls the tool to write the plan. This prevents single-agent bias and ensures your calendar matches your dietary goals.

Multi-agent recipe curation and cleanup

`update_recipe` allows your agents to collaboratively refine your database. One agent can flag formatting issues while another rewrites the instructions for clarity. For duplicates, a critic agent checks the output of `list_recipes` and coordinates with a deletion agent. They verify the match before calling `delete_recipe` to clean the database.

Automated shopping list negotiation via MCP Server

`create_shopping_list` is called after your agents cross-reference your meal plan with your current inventory. The agents debate which items are actually missing before building the final list. They use `toggle_shopping_list_item` to update your progress as you confirm items. This keeps your shopping workflow coordinated across multiple specialized agents.

Setup guide

Set up Mealie (Recipe Manager) 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 Mealie (Recipe Manager) 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="Mealie (Recipe Manager)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Mealie (Recipe Manager) 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="Mealie (Recipe Manager)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Mealie (Recipe Manager) 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 Mealie. 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 Mealie (Recipe Manager) 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 Mealie (Recipe Manager) MCP in AutoGen

Install autogen-ext[mcp] and use mcp_server_tools with StreamableHttpServerParams pointing to your Vinkius server. Pass the resulting tool list to your AssistantAgent.

Yes, they can use delete_meal_plan. You can set up a supervisor agent in your AutoGen group to review and approve all deletion calls before they hit your database.

One agent reads active lists using list_shopping_lists, while another processes the menu. They negotiate the changes and use toggle_shopping_list_item to update the state.

Yes. Your agents can query your setup using list_categories and list_tags, then apply the correct metadata to new recipes using update_recipe.

The MCP Server acts as a zero-trust broker, executing commands locally. Your recipe files, meal schedules, and shopping lists stay strictly inside your Mealie container without exposing your underlying database.

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