How to Use the Flagsmith MCP in LangChain

Q: How do I pass Flagsmith environment keys to a LangChain agent?

Set the FLAGSMITHENVIRONMENTKEY as an environment variable in your runtime before initializing the MCP server. LangChain then accesses getenvironmentflags automatically through the server adapter.

Q: Can a LangChain agent change multiple Flagsmith flags at once?

Yes, the agent uses updateflagv2 to apply batch updates inside a single chain step. This prevents multiple API roundtrips and keeps your flag updates atomic.

Q: How does LangSmith trace Flagsmith tool calls?

LangSmith logs every execution of tools like getidentityflags as a distinct step in the trace. You can inspect the input traits and the returned flag states directly in your dashboard.

Q: Can I manage environments dynamically using the MCP server?

Yes. Your agent can call createenvironment to spin up a new environment for a specific branch, then retrieve its configuration using getenvironmentdocument.

Control your application runtime by letting LangChain agents evaluate and toggle Flagsmith feature flags on the fly.

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 LangChain

Create your Vinkius account to connect Flagsmith 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 Flagsmith with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Link Flagsmith updates into LangChain reasoning chains

The `update_flag_v2` tool changes multiple feature states inside a single LangChain step. Your agent evaluates current run metrics, decides if a feature causes errors, and triggers a batch update immediately. You get complete visibility through LangSmith tracing to see exactly when the agent called `get_environment_flags` to inspect the state. Every step is logged, showing the exact parameters passed to the MCP server.

Target specific users during conversational steps

Use `identify_user` to attach specific traits to a user context during a live chat session. The agent tracks these traits to decide which specific code paths or prompts to expose next. Right after identifying them, the agent calls `get_identity_flags` to fetch the active flags for that exact user. This allows your chain to adapt its behavior based on individual user segments.

Automate staging environment setup inside chains

The `create_environment` tool lets your agent provision a new testing space using this MCP server when running integration tests. The agent handles the setup, runs the test suite, and tears down overrides if needed. If a test fails, the agent uses `delete_segment_override` to clean up dirty states before the next chain execution. This keeps your testing pipeline clean without manual dashboard intervention.

Setup guide

Set up Flagsmith 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 Flagsmith 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({
    "flagsmith-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 Flagsmith 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 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 LangChain

Set the FLAGSMITH_ENVIRONMENT_KEY as an environment variable in your runtime before initializing the MCP server. LangChain then accesses `get_environment_flags` automatically through the server adapter.

Yes, the agent uses `update_flag_v2` to apply batch updates inside a single chain step. This prevents multiple API roundtrips and keeps your flag updates atomic.

LangSmith logs every execution of tools like `get_identity_flags` as a distinct step in the trace. You can inspect the input traits and the returned flag states directly in your dashboard.

Yes. Your agent can call `create_environment` to spin up a new environment for a specific branch, then retrieve its configuration using `get_environment_document`.

This MCP server only passes user traits and identity keys to Flagsmith's API when calling `identify_user`. All operations run inside Vinkius's secure sandboxed isolates, meaning user traits never leak to external training sets.

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