How to Use the Fountain MCP in AutoGen

Q: How do I configure Fountain for AutoGen?

Run pip install -U autogen-extmcp. Use the StreamableHttpServerParams to fetch the tools and pass the adapter directly to your AssistantAgent.

Q: Can AutoGen agents review Fountain job posts together?

Yes. They can call listjobposts to retrieve published listings. A copywriter agent and an HR agent can then debate the effectiveness of the job descriptions.

Q: Can AutoGen track hired workers in Fountain?

Agents use listworkers to pull the active roster. They can analyze this data to determine if recent hires align with the original hiring goals.

Deploy multi-agent AutoGen systems to debate and optimize your Fountain hiring funnels.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fountain MCP to AutoGen

Create your Vinkius account to connect Fountain 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 Fountain with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen Agents Debate Hiring Goals

The `list_hiring_goals` tool feeds your targets into a multi-agent conversation. A performance agent pushes to increase hiring speed, while a compliance agent reviews the active pipeline to ensure quality standards. They negotiate using data from `list_workers` and `list_openings`. The agents cross-reference how many people you hired against how many roles remain open, debating the most efficient allocation of recruiting resources before presenting a final recommendation.

Audit Funnels with MCP Server Tools

Your agents map the recruitment pipeline by calling `list_funnels` and `list_funnel_stages`. One agent identifies bottlenecks in the background check stage, while another proposes workflow adjustments. They pull evidence using `list_interview_sessions` to see if scheduling delays cause candidate drop-off. The AutoGen framework forces these agents to challenge each other's conclusions until they reach a consensus on why the funnel is stalling.

Analyze Applicant Pools Collaboratively

The `list_applicants` tool gives your agents raw candidate volume to evaluate. They pull the list, and a specialized screening agent decides which profiles require deeper inspection. That agent then triggers `get_applicant` and `list_applicant_notes` to gather specific feedback. A secondary agent reviews the notes to check for recruiter bias or missed qualifications, ensuring no candidate gets rejected without deliberate, multi-perspective consideration.

Setup guide

Set up Fountain 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 Fountain 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="Fountain_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Run `pip install -U autogen-ext[mcp]`. Use the StreamableHttpServerParams to fetch the tools and pass the adapter directly to your AssistantAgent.

Yes. They can call `list_job_posts` to retrieve published listings. A copywriter agent and an HR agent can then debate the effectiveness of the job descriptions.

The MCP server provides the raw data. Agents pull organization attributes via `get_account_details` and use that context to ground their debates in your specific corporate constraints.

Agents use `list_workers` to pull the active roster. They can analyze this data to determine if recent hires align with the original hiring goals.

The server transmits scheduled interview times and applicant employment histories. We secure this transit using ephemeral sandbox environments that destroy the connection state immediately upon task completion.

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