How to Use the Freshworks MCP in AutoGen

Q: How do I configure Freshworks tools in AutoGen?

Install the autogen-extmcp package and initialize mcpservertools. Pass the returned list directly into your AssistantAgent constructor.

Q: How does AutoGen handle large Freshworks payloads?

When an agent calls listtickets, it receives the full JSON response in its context window. If the payload is too large, you should prompt the agent to request specific filters.

Q: Is my helpdesk data exposed to other agents?

Raw support requests from getticket are strictly confined to your specific session. The Vinkius architecture provisions a temporary, isolated environment that destroys all memory of the conversation the second your script terminates.

Build AutoGen teams that debate sales strategies and triage support tickets using live Freshworks data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshworks MCP to AutoGen

Create your Vinkius account to connect Freshworks 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 Freshworks with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen Agents Debate Sales Strategy

Your AutoGen agents use `list_deals` and `list_accounts` via the MCP Server to pull live pipeline metrics into their group chats. A risk-analysis agent reads the deal stages, while a forecasting agent argues about the likelihood of closing. They negotiate a final revenue projection based on the actual numbers. Instead of a single model guessing the outcome, you have specialized personas challenging each other. They use the server to fetch hard evidence from the CRM. When the debate finishes, you get a consensus that accounts for both optimism and historical churn.

Multi-Agent Ticket Resolution

The `list_tickets` and `get_ticket` tools feed raw customer complaints into a specialized support swarm. A technical agent analyzes the bug report, while a customer success agent evaluates the account's priority using `list_companies`. If the technical agent suggests a workaround that takes three days, the success agent pushes back because the client is a top-tier account. They arrive at a balanced response plan. The tools provide the factual grounding for their discussion.

Coordinate Cross-Department Contacts

Your system uses `list_crm_contacts` and `list_helpdesk_contacts` through this MCP connection to find discrepancies between sales and support databases. An auditing agent pulls lists from both sides and flags users who exist in one but not the other. A second agent reviews the flagged users and proposes merge operations. They use `list_agents` to figure out which human employee should approve the changes. The entire operation runs autonomously through structured conversation.

Setup guide

Set up Freshworks 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 Freshworks 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="Freshworks_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package and initialize `mcp_server_tools`. Pass the returned list directly into your `AssistantAgent` constructor.

Yes. You can provide the same tool list to every agent in your group chat. They will all have the ability to query the endpoints independently during their turn.

When an agent calls `list_tickets`, it receives the full JSON response in its context window. If the payload is too large, you should prompt the agent to request specific filters.

The setup relies on Streamable HTTP. Your multi-agent system communicates with the remote endpoints without managing local binaries.

Raw support requests from `get_ticket` are strictly confined to your specific session. The Vinkius architecture provisions a temporary, isolated environment that destroys all memory of the conversation the second your script terminates.

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