How to Use the Unleash (Feature Toggles) MCP in Pydantic AI

Q: How do I check flag status with Unleash (Feature Toggles) on Pydantic AI?

Call getclientfeatures to retrieve all active flags and strategies for evaluation. Because of the runtime validation, you are guaranteed that the returned feature data will match your defined models, which is a huge win for stability.

Q: Can I list projects using Unleash (Feature Toggles) with Pydantic AI?

Yes. Use listprojects to get every configured project ID. You then use listprojectfeatures to check the flags for a given project, and all results are type-validated on the way out.

Q: What data types are touched when I report metrics with Unleash (Feature Toggles) on Pydantic AI?

The metric reporting tools (reportclientmetrics and reportfrontendmetrics) touch flag usage metadata. Since everything is validated, you know the structure of the reported feature access data is correct.

Q: Does the MCP Server help me list all environments for Unleash (Feature Toggles) using Pydantic AI?

The listenvironments tool fetches every environment configured in Unleash. This helps you validate that your agent is correctly checking flags against the intended deployment context.

Q: What if I need to check flags for users? How does Unleash (Feature Toggles) work with Pydantic AI?

Use listusers first to get all configured user accounts. Then, pass this data into the feature tools like getclientfeatures. The validation ensures that the user context passed is exactly what your agent expects.

Ensure correctness when managing features with Unleash (Feature Toggles) using Pydantic AI.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safely evaluate feature flags for the agent.

The `get_client_features` tool fetches all active feature flags and strategies, ensuring your agent only sees data that matches your defined Pydantic models. This prevents silent corruption. If you need to pass context like a user ID or properties, use `get_frontend_features`. The validation layer confirms the structure of this input before the MCP Server processes it.

Scope flag checking by project IDs.

To see what projects are available, run `list_projects` to get all configured Unleash project IDs. You can then use `list_project_features` to fetch flags for a specific ID. This structured approach guarantees that the output data conforms to your expected schema, making type-safe development easier.

Log activity and usage metrics accurately.

Track usage with `report_client_metrics`, which allows your backend SDK instance to send flag usage data. Similarly, use `report_frontend_metrics` for logging frontend interactions. Both tools ensure that the reported metrics are validated against Pydantic models before they hit the MCP Server.

Setup guide

Set up Unleash (Feature Toggles) 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": {
        "unleash-feature-toggles-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Unleash (Feature Toggles) 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 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 Pydantic AI

Call `get_client_features` to retrieve all active flags and strategies for evaluation. Because of the runtime validation, you are guaranteed that the returned feature data will match your defined models, which is a huge win for stability.

Yes. Use `list_projects` to get every configured project ID. You then use `list_project_features` to check the flags for a given project, and all results are type-validated on the way out.

The metric reporting tools (`report_client_metrics` and `report_frontend_metrics`) touch flag usage metadata. Since everything is validated, you know the structure of the reported feature access data is correct.

The `list_environments` tool fetches every environment configured in Unleash. This helps you validate that your agent is correctly checking flags against the intended deployment context.

Use `list_users` first to get all configured user accounts. Then, pass this data into the feature tools like `get_client_features`. The validation ensures that the user context passed is exactly what your agent expects.

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