How to Use the GrowthBook MCP in LlamaIndex

Q: Can LlamaIndex agents toggle GrowthBook flags based on user queries?

Yes, by equipping your FunctionAgent with the togglefeature tool. When a user asks to enable a feature, the agent parses the intent and executes the tool to modify the flag state.

Q: How does LlamaIndex avoid stale GrowthBook index data?

You should set up a periodic pipeline that calls listenvironments and listfeatures to refresh your vector store. This ensures the agent always queries the absolute latest state of your release flags.

Q: Can I filter which GrowthBook projects are indexed?

Yes, you can use listprojects to get all workspace IDs, then apply an allowedtools filter or custom logic to only index specific projects in LlamaIndex.

Index your GrowthBook feature states into LlamaIndex to query your release configurations using semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GrowthBook MCP to LlamaIndex

Create your Vinkius account to connect GrowthBook 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 GrowthBook with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index GrowthBook configurations for RAG

The `list_features` tool retrieves your entire flag registry so LlamaIndex can convert your release rules into searchable vector embeddings. This prevents your agent from hallucinating flag names or environment configurations during complex retrieval tasks. By indexing the output of `get_feature`, your RAG pipeline can instantly answer questions about who has access to a specific beta. Your team can query the index in plain English instead of digging through the GrowthBook dashboard.

Query live environments via LlamaIndex MCP Server

The `list_environments` tool feeds your active deployment targets directly into the LlamaIndex query engine. This allows your agent to ground its decisions in actual, real-time environment configurations rather than outdated static files. If a developer asks which features are active in staging, the agent queries the index, calls `get_project` to verify ownership, and returns a verified list. This live context ensures your documentation and actual deployment state never drift apart.

Clean up stale flags with semantic search

The `delete_feature` tool can be triggered automatically when LlamaIndex identifies abandoned flags in your codebase. The agent searches your indexed code repositories, matches them against active flags, and flags candidates for deletion. Once confirmed, the agent executes `update_feature` to archive the flag before final removal by configuring the MCP server to run hygiene checks. This automated hygiene keeps your GrowthBook workspace clean and prevents performance degradation from bloated flag payloads.

Setup guide

Set up GrowthBook 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 GrowthBook 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 GrowthBook tools.",
)
response = await agent.run("List recent GrowthBook 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 GrowthBook. 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 GrowthBook 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 GrowthBook MCP in LlamaIndex

Use the llama-index-tools-mcp package to connect to the GrowthBook server endpoint. Fetch your flag configurations using `list_features` and load the resulting documents directly into your vector index.

Yes, by equipping your FunctionAgent with the `toggle_feature` tool. When a user asks to enable a feature, the agent parses the intent and executes the tool to modify the flag state.

You should set up a periodic pipeline that calls `list_environments` and `list_features` to refresh your vector store. This ensures the agent always queries the absolute latest state of your release flags.

Yes, you can use `list_projects` to get all workspace IDs, then apply an allowed_tools filter or custom logic to only index specific projects in LlamaIndex.

Your environment layouts and flag rules are processed locally within your LlamaIndex runtime. The Vinkius MCP integration acts as a secure proxy, ensuring your sensitive configuration details are never sent to third-party vector providers.

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