How to Use the DevCycle MCP in LangChain

Q: Can LangChain agents modify DevCycle flags?

Yes. Agents use updatefeatureflagstatus to change flag states. You should configure human-in-the-loop approval steps in your chain for production environments.

Build LangChain reasoning pipelines that query, analyze, and update DevCycle feature flags automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DevCycle MCP to LangChain

Create your Vinkius account to connect DevCycle 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 DevCycle with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect the DevCycle MCP Server

The DevCycle MCP Server lets your LangChain agents interact directly with feature flags. You start a chain by running `list_devcycle_projects` to grab project IDs. The agent passes those IDs downstream to `list_project_environments` to map out your staging and production setups. Tool outputs feed straight into the next step. Your ReAct agent checks `list_active_flags`, spots an anomaly, and pulls the exact targeting rules using `get_feature_flag_details`. Everything stays visible inside LangSmith so you know exactly why a flag was queried.

Automated Rollout Pipelines

Automated rollouts rely on `search_feature_flags` to find specific release toggles inside your LangChain pipelines. Once located, the agent runs `get_environment_sdk_keys` to grab the right access credentials for the targeted environment. The chain decides what happens next based on your logic. If a performance metric drops in a connected database step, the agent instantly executes `update_feature_flag_status` to archive or disable the flag. You build the triggers, and the agent flips the switch.

Variable and Configuration Audits

Your agent calls `list_feature_variables` to map every defined variable in a project during complex configuration audits. It then loops through `list_feature_flags` to see which flags actually use them in live environments. This creates a fully automated audit trail. The agent documents unused variables, identifies stale configurations, and outputs a clean report. You stop manually checking dashboards because the chain does the heavy lifting.

Setup guide

Set up DevCycle 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 DevCycle 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({
    "devcycle-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 DevCycle 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 DevCycle. 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 DevCycle 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 DevCycle MCP in LangChain

Use MultiServerMCPClient with your DevCycle MCP server URL. Call client.get_tools() and pass the resulting tools into your agent creation function.

Yes. Agents use update_feature_flag_status to change flag states. You should configure human-in-the-loop approval steps in your chain for production environments.

LangChain handles the reasoning while the MCP server handles the schema. You skip writing custom API wrappers and let the agent decide when to call get_project_details.

Every tool execution logs automatically. You see the exact inputs sent to DevCycle and the raw JSON returned.

This server only accesses configuration metadata like project IDs and feature flag rules. It reads targeting logic via get_feature_flag_details but never touches your actual application payload or end-user PII. Authentication requires a single endpoint token kept completely isolated in the Vinkius V8 sandbox.

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