How to Use the Edamam Extended MCP in AutoGen

Q: How do I load Edamam Extended into AutoGen?

Run pip install -U "autogen-extmcp". Use StreamableHttpServerParams to define your URL, call mcpservertools, and pass the tools to your AssistantAgent.

Let multiple AutoGen agents debate meal plans using the Edamam Extended API.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Edamam Extended MCP to AutoGen

Create your Vinkius account to connect Edamam Extended 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 Edamam Extended with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent nutrition with the AutoGen MCP Server

The `search_recipes` tool fetches meals from a 3-million recipe catalog using specific filters. One agent pulls the recipes, while another agent critiques them based on the user's stated goals. This creates consensus-driven meal planning. A fitness agent pushes for high-protein options, while a budget agent flags expensive ingredients. They negotiate using the MCP Server data until they agree on a final weekly menu.

Verify macros via agent consensus

The `analyze_nutrition` tool calculates exact nutritional facts for any provided recipe. Your agents use this to double-check each other's work. If the creative agent suggests a substitution, the analytical agent runs the new ingredient list through the tool. If the macros fall outside the target range, the analytical agent rejects the proposal. The conversation continues until the math works.

Standardize food inputs automatically

The `parse_food` tool cross-references raw text against a 900,000-item food database. Your AutoGen system uses this to resolve ambiguous ingredients during a debate. When one agent says a cup of rice, the verification agent calls the tool to get the exact caloric value of white versus brown rice. The adapter handles the schema conversion automatically, keeping the agents focused on the logic.

Setup guide

Set up Edamam Extended 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 Edamam Extended 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="Edamam Extended_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Run `pip install -U "autogen-ext[mcp]"`. Use `StreamableHttpServerParams` to define your URL, call `mcp_server_tools`, and pass the tools to your `AssistantAgent`.

Yes. The framework automatically converts the Edamam JSON schemas into native tool descriptions. The agents read these descriptions to understand what parameters they need.

They call it sequentially during their turn in the conversation. One agent fetches the data, and the others read the output from the shared chat history.

Yes. While HTTP is common for remote servers, the framework supports both `stdio` and `Streamable HTTP` transports depending on your architecture.

The tools process search strings, food names, and recipe URLs. Vinkius secures this by routing all requests through a stateless proxy. No payload data is ever written to disk or logged outside the active MCP execution window.

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