How to Use the Mode (Collaborative Data Platform) MCP in LlamaIndex

Q: How do I index Mode (Collaborative Data Platform) metadata with LlamaIndex?

You use llama-index-tools-mcp to load the tools into your LlamaIndex setup using this MCP client. The framework calls listreports to gather metadata and indexes it directly into your vector database.

Q: Can I run semantic search on Mode (Collaborative Data Platform) spaces using LlamaIndex?

Yes, you can. LlamaIndex indexes the output of listspaces and getspace, allowing you to run natural language queries to locate specific analytics collections.

Q: How does LlamaIndex handle rate limits on Mode (Collaborative Data Platform) tools?

LlamaIndex caches the indexed output of listreports and searchreports in your vector store. This minimizes direct calls to the Mode API, protecting you from rate limits.

Index your Mode reports into LlamaIndex vector stores to query live analytical metadata without hallucinations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mode (Collaborative Data Platform) MCP to LlamaIndex

Create your Vinkius account to connect Mode (Collaborative Data Platform) 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 Mode (Collaborative Data Platform) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG indexes from Mode reports using this MCP Server

This MCP server provides `list_reports` to let your LlamaIndex pipeline pull report metadata and index it directly into a vector store. Storing these records locally turns static report lists into a searchable knowledge base for your local agents. When a user asks a question, the agent queries the index first, then uses `get_report` to fetch the fresh parameters. You get answers grounded in actual database configurations, not model guesses.

Semantic search across spaces and data sources

The `search_reports` tool lets your agent query the Mode API directly to locate specific charts. LlamaIndex then maps these search results to your existing vector indexes to find related spaces. By using `list_spaces` and `get_space`, the framework builds a semantic map of your entire analytics structure. Your agent can then guide users to the right space without them needing to browse the UI.

Audit workspace members and database connectors

Running `list_members` and `list_data_sources` allows your agent to index who has access to which database connectors. The framework stores these relationships as nodes in your knowledge graph. This lets you build compliance agents that query the graph to see which analysts are connected to sensitive databases. You get instant answers about your workspace security posture.

Setup guide

Set up Mode (Collaborative Data Platform) 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 Mode (Collaborative Data Platform) 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 Mode (Collaborative Data Platform) tools.",
)
response = await agent.run("List recent Mode (Collaborative Data Platform) 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 Mode. 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 Mode (Collaborative Data Platform) 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 Mode (Collaborative Data Platform) MCP in LlamaIndex

You use `llama-index-tools-mcp` to load the tools into your LlamaIndex setup using this MCP client. The framework calls `list_reports` to gather metadata and indexes it directly into your vector database.

Yes, you can. LlamaIndex indexes the output of `list_spaces` and `get_space`, allowing you to run natural language queries to locate specific analytics collections.

LlamaIndex caches the indexed output of `list_reports` and `search_reports` in your vector store. This minimizes direct calls to the Mode API, protecting you from rate limits.

It lets your pipeline map which database connectors feed your reports. Your RAG applications can then tell users exactly where their data comes from.

Your report metadata and space configurations remain completely private. The MCP server runs within an isolated V8 sandbox on Vinkius, ensuring your data never leaks to public LLMs.

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