How to Use the Clari MCP in LangChain

Q: How do I use Clari tools in a LangChain ReAct agent?

First, get the tools from the client with client.gettools(). Then, pass that tool list directly into the createagent function. LangChain's ReAct framework will automatically know how to call the Clari tools based on the prompt.

Q: What's the best way to monitor Clari forecast changes with LangChain?

Create a simple chain that periodically calls listclariforecasts. Have the agent compare the new output to the previous run. If it detects a difference, it can trigger another chain to send a notification or log the details.

Chain Clari API calls together to build revenue-aware agents in LangChain.

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 LangChain

Create your Vinkius account to connect Clari to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Forecast Accuracy

Build a chain that checks if your team's forecast matches reality. The agent starts by calling `list_clari_time_periods` to find the last quarter, then uses `list_clari_forecasts` to pull the final submitted numbers for that period. Then, the chain's next step is to call `list_revenue_opportunities` with the same time period, filtering for deals that actually closed. Your agent can then compare the forecast to the closed-won revenue, giving you a clear picture of your team's accuracy without manual report-building.

Drill Down on At-Risk Deals

Don't just get a list of deals; get the story behind them. A LangChain agent can use `list_revenue_opportunities` to scan for deals with a low health score or a recently pushed close date. It flags these automatically. For each flagged deal, the agent then passes the opportunity ID directly into `get_opportunity_revenue_details`. This second step in the chain fetches the granular data—deal size, next steps, and CRM notes—so you get a full briefing on what's going wrong, instantly.

Build an Audit Agent with this MCP Server

Keep an eye on important changes in your pipeline. You can build a specialized agent that monitors the output of `list_clari_audit_logs` for specific events, like a deal's forecast category changing from 'Commit' to 'Best Case'. Once your agent spots a change, it can trigger a new chain of actions. It could use `list_clari_users` to find out who made the change and `get_opportunity_revenue_details` to see the full context of the opportunity that was modified. It’s an automated watchdog for your pipeline.

Setup guide

Set up Clari MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Clari tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "clari-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Clari transactions"
    })
    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 LangChain

First, get the tools from the client with `client.get_tools()`. Then, pass that tool list directly into the `create_agent` function. LangChain's ReAct framework will automatically know how to call the Clari tools based on the prompt.

Yes. That's what chains are for. You can have one step in your chain call `list_revenue_opportunities` from this MCP Server, then pass the results to another tool that queries your internal SQL database or a different API.

Create a simple chain that periodically calls `list_clari_forecasts`. Have the agent compare the new output to the previous run. If it detects a difference, it can trigger another chain to send a notification or log the details.

Yes, any tool call made through the LangChain adapter is fully traceable in LangSmith. You'll see the exact inputs, outputs, latency, and token usage for every call to a Clari tool, right alongside your other chain components.

Your data's security is handled at the transport layer. Vinkius manages the connection to your Clari instance with a single endpoint token. The revenue and forecast data you request only exists within the context of your agent's current, stateless execution and isn't stored by the MCP server.

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