How to Use the DevCycle MCP in Pydantic AI

Q: How do I configure DevCycle with Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to your Vinkius HTTP endpoint. Pass this toolset into your Agent definition. Note that MCPServerHTTP is deprecated in favor of the unified toolset approach.

Bring strict type safety to DevCycle rollouts by connecting Pydantic AI to this verified MCP Server.

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 Pydantic AI

Create your Vinkius account to connect DevCycle to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Feature Flagging

Silent failures in feature management cause production outages. Pydantic AI forces every response from `get_feature_flag_details` into a strict model. If DevCycle returns an unexpected rule schema, your agent fails loudly instead of hallucinating a targeting decision. This matters when you automate state changes. Before the agent triggers `update_feature_flag_status`, the framework validates the payload. You know exactly what variation is being applied because the types guarantee the data structure matches your expectations.

Map Your DevCycle MCP Server

Agents need context to navigate complex rollouts. Yours starts by running `list_devcycle_projects` and `get_project_details` to build a mental map of your workspace. It parses the exact variables available via `list_feature_variables` before attempting any configuration. Finding specific toggles is fast. The agent executes `search_feature_flags` with targeted keywords. It filters the results through your Pydantic models, discarding irrelevant flags and focusing only on what matches your deployment criteria.

Audit Active Environments

You need to know what is running where. The agent queries `list_project_environments` to grab the IDs, then maps the active state using `list_active_flags`. It builds a complete, type-validated matrix of your current release posture. When downstream services need access, the agent retrieves the exact credentials via `get_environment_sdk_keys`. It passes these keys into your application logic safely, ensuring no malformed strings break your initialization sequence.

Setup guide

Set up DevCycle MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "devcycle-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to DevCycle tools.",
)

result = await agent.run("List recent DevCycle transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset into your `Agent` definition. Note that `MCPServerHTTP` is deprecated in favor of the unified toolset approach.

The MCP protocol handles the raw JSON, and Pydantic AI validates the tool execution results against the schema defined by the server. If the agent tries to pass a string to an integer field in `update_feature_flag_status`, it throws a validation error immediately.

Yes. Pydantic AI is model-agnostic. You can connect a local Llama model to this MCP Server, and it will interact with `list_feature_flags` just like an OpenAI or Anthropic model would.

Predictability. Feature flags control live application behavior. By enforcing strict schemas on tools like `get_feature_flag_details`, you eliminate the risk of an agent misinterpreting a boolean targeting rule.

Only your connected agent. The Vinkius zero-trust architecture ensures that when `get_environment_sdk_keys` runs, the payload routes directly to your client. No third party logs your keys, and the isolated container drops all state after 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

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript