How to Use the Clari MCP in LlamaIndex

Q: How do I create a LlamaIndex vector index from my Clari opportunities?

First, use the McpToolSpec to get the Clari tools. Then, call a tool like listrevenueopportunities and pass its JSON output directly into a VectorStoreIndex. LlamaIndex handles the parsing and embedding for you.

Q: Can I use LlamaIndex to ask questions about historical Clari data?

Yes. Periodically run tools like listclariforecasts, save the results, and add them to a LlamaIndex data structure. This lets your agent query trends and compare data across different points in time.

Q: What's the setup for using the Clari MCP Server with a LlamaIndex FunctionAgent?

It's straightforward. Instantiate the McpToolSpec with your client, get the tools with totoollistasync(), and pass that list when creating your FunctionAgent. The agent will then have access to all the Clari functions.

Ground your LlamaIndex RAG agents in live Clari revenue and forecast data.

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 LlamaIndex

Create your Vinkius account to connect Clari to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Sales Pipeline

Turn your active pipeline into a searchable knowledge base. Use the Clari MCP tools to pull data with `list_revenue_opportunities` and `list_revenue_accounts`. LlamaIndex takes that raw data and indexes it into a vector store you control. Now your RAG agent can answer complex questions that a simple API call can't handle. Ask things like, 'Which of our enterprise accounts in the finance sector have deals slipping this quarter?' and get an answer based on real data.

Create a Historical Forecast Index

Don't let past performance data disappear. Set up a simple process to run `list_clari_forecasts` every week and feed the output into a LlamaIndex vector store. This builds a history of your forecast submissions over time. With this index, your agent can analyze trends, compare forecast accuracy quarter over quarter, and spot which reps are consistently over- or under-calling their number. It's business intelligence without the dashboards.

Query Your Clari Configuration

This isn't just for revenue data. You can index operational information by running tools like `list_clari_users` and `list_clari_time_periods`. This creates a snapshot of your account's structure and settings. Once indexed, your LlamaIndex agent can answer internal questions like 'Who is in the EMEA sales hierarchy?' or 'What were our exact fiscal dates for last year?' without needing to hit the live API every single time.

Setup guide

Set up Clari MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Clari MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Clari tools.",
)
response = await agent.run("List recent Clari data")

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 LlamaIndex

First, use the `McpToolSpec` to get the Clari tools. Then, call a tool like `list_revenue_opportunities` and pass its JSON output directly into a `VectorStoreIndex`. LlamaIndex handles the parsing and embedding for you.

Yes. Periodically run tools like `list_clari_forecasts`, save the results, and add them to a LlamaIndex data structure. This lets your agent query trends and compare data across different points in time.

It's straightforward. Instantiate the `McpToolSpec` with your client, get the tools with `to_tool_list_async()`, and pass that list when creating your `FunctionAgent`. The agent will then have access to all the Clari functions.

You decide. You can have the agent call the Clari tools directly for live data, or you can have it query the index you've built from past tool calls for historical context. You can even combine both in the same query.

You are in control of your indexed data. The MCP server provides secure, ephemeral transport for opportunity and revenue data from Clari. Once you use LlamaIndex to create a vector store, that indexed data resides in your own infrastructure, subject to your security policies.

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