How to Use the Unleash (Feature Toggles) MCP in LangChain

Q: How do I list all possible environments with Unleash (Feature Toggles) and LangChain?

Just call listenvironments. This fetches every environment configured in the MCP Server. Your agent can then use this list to scope down flag checks, making sure you're targeting the right deployment.

Q: Can I find all available projects using Unleash (Feature Toggles) and LangChain?

Yes, you use the listprojects tool. It returns every project configured in the system. This list is crucial for building pipelines that handle multi-product environments.

Q: How do I register new SDK instances with Unleash (Feature Toggles) and LangChain?

You use registerclient to register a new backend SDK instance. This step initializes the connection for reporting or evaluation, making sure your agent has the necessary endpoint token.

Q: If I need to know about feature segments, what tool should I use with Unleash (Feature Toggles) and LangChain?

Use listsegments. This function fetches every segment configured in Unleash. You can then pass these segment details into the main MCP Server logic to narrow down flag evaluation.

Control your product launch logic with Unleash (Feature Toggles) using LangChain's multi-step reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unleash (Feature Toggles) MCP to LangChain

Create your Vinkius account to connect Unleash (Feature Toggles) 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 Unleash (Feature Toggles) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Feature Flags via `get_client_features`

Use `get_client_features` to pull all feature flags and strategies the server uses. This output immediately informs your agent about current product states. Your LangChain pipeline can then pass that list—say, a specific flag name or strategy type—directly into subsequent tool calls. It’s perfect for building complex reasoning where one configuration check triggers another.

Track Project and Environment Context

Need to scope down the flags? Start by calling `list_projects` to pull every configured project ID. From there, you can use `get_frontend_features` or `get_client_features` with a specific project context. This process ensures your agent only evaluates features relevant to the current deployment target, keeping the logic clean and focused.

Monitor Usage Metrics for Your MCP Server

You can monitor how frequently flags are used by calling `report_client_metrics` or `report_frontend_metrics`. This gives your agent visibility into real-world usage patterns. The data returned helps you decide which features need more monitoring, allowing the LangChain agent to build smarter reporting chains for product teams.

Setup guide

Set up Unleash (Feature Toggles) 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 Unleash (Feature Toggles) 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({
    "unleash-feature-toggles-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 Unleash (Feature Toggles) 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 Unleash. 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 Unleash (Feature Toggles) 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 Unleash (Feature Toggles) MCP in LangChain

Just call `list_environments`. This fetches every environment configured in the MCP Server. Your agent can then use this list to scope down flag checks, making sure you're targeting the right deployment.

This server manages user configuration details. Specifically, it handles listing all configured users via `list_users`. This lets your agent check if a given user ID exists before evaluating feature flags.

Yes, you use the `list_projects` tool. It returns every project configured in the system. This list is crucial for building pipelines that handle multi-product environments.

You use `register_client` to register a new backend SDK instance. This step initializes the connection for reporting or evaluation, making sure your agent has the necessary endpoint token.

Use `list_segments`. This function fetches every segment configured in Unleash. You can then pass these segment details into the main MCP Server logic to narrow down flag evaluation.

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