How to Use the Freshteam MCP in AutoGen

Q: How do I load Freshteam tools into my AutoGen workspace?

Install the MCP extension for AutoGen. Use mcpservertools with standard HTTP parameters to fetch the endpoints, then pass that tool list into your AssistantAgent constructor.

Give your AutoGen agents the ability to debate, review, and execute Freshteam HR actions autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshteam MCP to AutoGen

Create your Vinkius account to connect Freshteam 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 Freshteam with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen agents for HR operations

The Freshteam MCP Server turns your static HR workflows into active multi-agent negotiations. A recruiting agent can call `list_job_postings` to find open roles, while a finance agent cross-references `list_departments` to verify budget availability. They talk to each other before making a move. If the recruiter wants to move forward, the compliance agent reviews the candidate's background via `get_applicant_details` and flags any missing documentation before giving the green light.

Consensus-driven onboarding

Using `create_employee_record` requires absolute precision, and multi-agent setups excel here. An onboarding agent drafts the payload, but a secondary reviewer agent checks it against `list_job_roles` to prevent title mismatches. This stops bad data from entering your HRIS. The MCP tools provide the exact ground truth, and the agents debate the schema validity until they reach a consensus that the new hire profile is perfectly formatted.

Managing leave and coverage

You can build a scheduling group that monitors `list_time_off_requests` and `list_employees` to predict capacity shortages. The agents pull the leave data and argue over who should cover the empty shifts. Before they execute any final schedule adjustments, a diagnostic agent runs `check_hris_status` to confirm the API is responding. This built-in redundancy keeps your HR operations running even when edge cases pop up.

Setup guide

Set up Freshteam 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 Freshteam 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="Freshteam_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the MCP extension for AutoGen. Use `mcp_server_tools` with standard HTTP parameters to fetch the endpoints, then pass that tool list into your AssistantAgent constructor.

The adapter handles schema conversion behind the scenes. Your agents read the parameter requirements natively, so they know exactly what strings or integers to pass to the HR endpoints.

You set human-in-the-loop policies at the agent level. The system will pause and ask for your approval in the console before the agent actually fires the write command to the server.

Streamable HTTP transport works best for cloud deployments. If you are running the agents locally for testing, standard input/output transport is also fully supported.

The V8 Isolate Sandbox ensures that when your agent fetches personal contact info from the employee directory, the execution environment remains isolated. Vinkius drops the container the moment the conversation thread terminates, leaving no residual data.

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