How to Use the DevCycle MCP in Mastra AI

Q: Can I force human approval for DevCycle actions in Mastra AI?

Absolutely. Use the requireToolApproval setting on your agent to force a human to sign off before updatefeatureflagstatus is executed.

Build complex release workflows in Mastra AI with autonomous DevCycle flag management.

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 Mastra AI

Create your Vinkius account to connect DevCycle to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional flag logic in Mastra AI

Create automated workflows that react to feature flag changes. Your Mastra AI agent can call `list_feature_flags` as a trigger, then execute conditional logic based on the returned status. This allows for self-healing pipelines. If a flag is disabled, the agent uses `get_feature_flag_details` to verify targeting rules before deciding to halt or continue a deployment.

Systematic flag cleanup

Reduce technical debt by letting your agent find unused flags. By calling `search_feature_flags` across your projects, the agent identifies candidates for archival. This keeps your DevCycle dashboard clean. Once identified, the agent uses `update_feature_flag_status` to archive the flag, ensuring your production environment stays lean.

Environment-aware agent execution

Connect your agents to specific production or staging environments with ease. The `list_project_environments` tool lets your agent scope its actions to the correct target. Once the environment is confirmed, the agent retrieves the necessary `get_environment_sdk_keys` to authenticate its operations. It ensures that no agent accidentally touches the wrong project infrastructure.

Setup guide

Set up DevCycle MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All DevCycle tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "devcycle-mcp-client",
  servers: {
    "devcycle-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "DevCycle Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to DevCycle tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent DevCycle transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI supports automatic retries and exponential backoff. If an API call to DevCycle fails, the workflow engine manages the retry logic for you.

Absolutely. Use the `requireToolApproval` setting on your agent to force a human to sign off before `update_feature_flag_status` is executed.

It does. Each tool is designed to be chained, allowing for multi-step sequences like checking a project, listing its flags, and updating a specific status.

The server operates in a zero-trust sandbox. Your project details are kept in memory only for the duration of the agent's task.

We do not store your flag settings. The MCP Server only touches your flag definitions to relay them to the agent during execution.

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