How to Use the Clari MCP in AutoGen

Q: How can I make two AutoGen agents argue about a Clari forecast?

Give them different instructions and tools. Provide the listclariforecasts tool to an 'Optimist' agent and the listrevenueopportunities tool to a 'Pessimist' agent. Then, give them a prompt that forces them to reconcile their different data points.

Q: What's a good multi-agent setup for auditing Clari data with AutoGen?

Create a UserProxyAgent to represent you and an AssistantAgent for the work. Pass the Clari tools from this MCP Server to the assistant. Then, ask it to 'Find any deals over $100k that slipped from Commit last week' and it will use the tools to find an answer.

Q: Can I create an AutoGen agent that only has permission to list Clari users?

Yes. When you get the list of tools from mcpservertools, you can filter it before passing it to an agent's constructor. This way, you can create a specialized agent that only has access to listclariusers and nothing else.

Q: How do I pass Clari tools to an AutoGen AssistantAgent?

Use the mcpservertools function from the autogen-ext library to get the tool definitions. The function returns a list of functions that you can pass directly to the tools parameter of your AssistantAgent.

Let your AutoGen agents debate Clari sales data to find the best path to quota.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clari MCP to AutoGen

Create your Vinkius account to connect Clari 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 Clari with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate the Forecast

Set up a team of agents to stress-test your forecast. Create a 'Sales Analyst' agent that uses `list_clari_forecasts` to pull the current numbers. Then, create a 'Risk Analyst' agent that uses `list_revenue_opportunities` to find deals with low health scores or pushed close dates. In the ensuing conversation, the Risk Analyst challenges the forecast based on the underlying deal data. They debate back and forth, arriving at a consensus number that's more realistic than a single agent's opinion.

Run a Multi-Agent Pipeline Review

Automate your deal review process with a team of specialist agents. A 'Manager' agent can kick off the process by selecting a high-value deal. It then tasks an 'Analyst' agent to call `get_opportunity_revenue_details` for a deep dive. At the same time, a 'Compliance' agent checks `list_clari_audit_logs` for any recent changes to that same deal. They report their findings back to the Manager, who gets a multi-faceted view of the opportunity's health and history.

Automate Account Intelligence

Get your agents to prep you for your next big meeting. A 'Planner' agent can start by using `list_revenue_accounts` to pick a target account. It then instructs a 'Researcher' agent to find all associated deals using `list_revenue_opportunities`. These two agents collaborate, pulling together a concise brief on the account's entire pipeline. The conversation between them produces a summary that gives you a complete picture before you even open your CRM.

Setup guide

Set up Clari 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 Clari 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="Clari_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Give them different instructions and tools. Provide the `list_clari_forecasts` tool to an 'Optimist' agent and the `list_revenue_opportunities` tool to a 'Pessimist' agent. Then, give them a prompt that forces them to reconcile their different data points.

Create a `UserProxyAgent` to represent you and an `AssistantAgent` for the work. Pass the Clari tools from this MCP Server to the assistant. Then, ask it to 'Find any deals over $100k that slipped from Commit last week' and it will use the tools to find an answer.

Yes. When you get the list of tools from `mcp_server_tools`, you can filter it before passing it to an agent's constructor. This way, you can create a specialized agent that only has access to `list_clari_users` and nothing else.

Use the `mcp_server_tools` function from the `autogen-ext` library to get the tool definitions. The function returns a list of functions that you can pass directly to the `tools` parameter of your `AssistantAgent`.

Access is controlled by you at the agent level. Since you explicitly assign tools to each agent, you can create roles. An 'Audit' agent might get `list_clari_audit_logs`, but a 'Sales' agent won't, preventing it from accessing sensitive logs about revenue or user 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