How to Use the FormKeep MCP in AutoGen

Q: How do I configure FormKeep for AutoGen?

Run pip install -U "autogen-extmcp". Use mcpservertools with your HTTP server parameters, and pass the tools list to your AssistantAgent constructor.

Build multi-agent systems that debate and manage your FormKeep data with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FormKeep MCP to AutoGen

Create your Vinkius account to connect FormKeep 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 FormKeep with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent AutoGen form processing

The `list_submissions` tool feeds raw user inputs directly into your multi-agent debate loop. A summarization agent reads the entries while a compliance agent checks them for sensitive information. They negotiate the outcome before taking action. If the compliance agent flags a record, it signals another agent to execute `delete_submission` to remove the liability from your database.

Map endpoints autonomously

Your agents use `list_forms` and `get_form_details` to understand your backend structure without human input. They read the schema definitions and figure out which forms contain the relevant data for the current task. You just provide the MCP Server connection. The `McpToolAdapter` handles all schema conversions automatically, letting your agents format their API requests correctly on the first try.

Audit individual submissions

When a debate requires deep context, an agent calls `get_submission` to pull the complete JSON payload of a specific entry. The agents argue over the specific field values rather than abstract summaries. This creates a highly resilient data processing system. Competing perspectives ensure that destructive actions only happen when all agents reach a consensus based on the actual API data.

Setup guide

Set up FormKeep 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 FormKeep 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="FormKeep_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Run `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with your HTTP server parameters, and pass the tools list to your `AssistantAgent` constructor.

Yes. You assign the tool list to specific agents in your swarm. A reader agent might get `list_submissions`, while an admin agent holds the keys to `delete_submission`.

No. AutoGen handles the translation natively. The framework reads the tool schemas and formats the agent outputs to match the API requirements perfectly.

You can connect using standard stdio or Streamable HTTP transports. The HTTP approach works best for distributed agent deployments.

Your form metadata and user entries remain entirely private. The MCP connection relies on a strict zero-trust model where authentication is handled at the network edge, keeping the actual payload isolated from unauthorized agents.

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