How to Use the Flagsmith MCP in LlamaIndex

Q: How does LlamaIndex index Flagsmith configuration documents?

LlamaIndex uses the getenvironmentdocument tool to pull the raw configuration JSON. It then parses and indexes this data into your vector store for semantic search queries.

Q: Can I query a user's Flagsmith traits using LlamaIndex?

Yes. The agent calls getidentityflags to retrieve the traits, which LlamaIndex inserts into the query context to personalize search results.

Q: How do I update a flag based on LlamaIndex search results?

When your index reveals an anomaly, the agent calls updateflagv1 to toggle the flag. This automates feature management based on live retrieval data.

Q: Can I fetch all default flags at once using this MCP server?

Yes, the getenvironmentflags tool retrieves all default states in one call. LlamaIndex can then store this snapshot to reference during user sessions.

Q: How is my Flagsmith API key secured during indexing?

Your FLAGSMITHAPIKEY is stored as an encrypted environment variable in the Vinkius isolate. This MCP server only uses it to authorize calls like updateflagv2 and never gets indexed or exposed in search metadata.

Index live Flagsmith configuration states directly into your LlamaIndex vector store for real-time RAG queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flagsmith MCP to LlamaIndex

Create your Vinkius account to connect Flagsmith 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 Flagsmith with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Flagsmith environment states for LlamaIndex RAG

The `get_environment_document` tool pulls your entire environment setup into a queryable document using the MCP server. LlamaIndex indexes this configuration so your agent can answer questions about active flag states. Instead of guessing which features are live, the agent queries the local vector index to verify. This avoids making redundant external API calls during complex reasoning tasks.

Ground user queries in live identity configurations

The `get_identity_flags` tool retrieves the current flag states and traits for a specific user ID. LlamaIndex stores this output in the conversation memory to ground subsequent responses. The agent checks these cached traits before suggesting actions to the user. This ensures the agent never recommends a feature that is disabled for that specific profile.

Sync state changes back to the feature platform

The `update_flag_v1` tool lets your indexing pipeline update a specific flag based on data trends via MCP. If the index detects a high error rate, the agent triggers a flag change to disable the feature. You can also use `delete_segment_override` when a segment's behavior no longer matches the indexed user data. This keeps your remote configuration aligned with your vector store insights.

Setup guide

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

LlamaIndex uses the `get_environment_document` tool to pull the raw configuration JSON. It then parses and indexes this data into your vector store for semantic search queries.

Yes. The agent calls `get_identity_flags` to retrieve the traits, which LlamaIndex inserts into the query context to personalize search results.

When your index reveals an anomaly, the agent calls `update_flag_v1` to toggle the flag. This automates feature management based on live retrieval data.

Yes, the `get_environment_flags` tool retrieves all default states in one call. LlamaIndex can then store this snapshot to reference during user sessions.

Your FLAGSMITH_API_KEY is stored as an encrypted environment variable in the Vinkius isolate. This MCP server only uses it to authorize calls like `update_flag_v2` and never gets indexed or exposed in search metadata.

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