How to Use the Flagsmith MCP in Pydantic AI

Q: How do I register the Flagsmith MCP Server in Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp". Use the unified MCPToolset class with your Vinkius HTTP endpoint, then pass that toolset directly to your Agent constructor.

Q: Is the legacy MCPServerHTTP class supported for Flagsmith in Pydantic AI?

No, MCPServerHTTP is deprecated in the latest versions of Pydantic AI. You must use the unified MCPToolset class to connect your agent to the Vinkius endpoint.

Q: How does this server secure my user trait data?

User traits processed by identifyuser are validated in memory and sent over HTTPS. Vinkius runs the MCP Server inside an ephemeral V8 Isolate sandbox, ensuring no user data is cached or stored permanently on the host.

Validate Flagsmith flag states and user traits at runtime with type-safe Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flagsmith MCP to Pydantic AI

Create your Vinkius account to connect Flagsmith 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 Flagsmith with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Flagsmith MCP Server schema validation

The `get_identity_flags` tool fetches active flags and traits for a specific user with strict schema enforcement. This tool returns structured data that Pydantic AI validates against your defined Python models at runtime. If this MCP Server returns an unexpected data type or a missing field, the agent fails loudly immediately. This prevents corrupted configurations from silently breaking your downstream application logic.

Update flags with strict validation checks

The `update_flag_v1` tool performs single flag modifications while ensuring the payload matches your strict schema. This tool lets your agent safely change flag values, enabled states, or segment rules. By using Pydantic models to construct the input, you ensure your agent never sends malformed payloads to the API. The framework catches validation errors before the request ever leaves your server.

Identify users and validate traits safely

The `identify_user` tool registers user identities and sets traits using strict type validation. This tool ensures that user profiles contain the exact data types your targeting rules require. Because Pydantic AI is model-agnostic, you can use this validation pipeline with OpenAI, Anthropic, or local models. The framework guarantees that whatever model you choose, the output format remains perfectly structured.

Setup guide

Set up Flagsmith 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": {
        "flagsmith-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Flagsmith 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 Flagsmith. 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 Flagsmith 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 Flagsmith MCP in Pydantic AI

Install the package using `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` class with your Vinkius HTTP endpoint, then pass that toolset directly to your `Agent` constructor.

No, `MCPServerHTTP` is deprecated in the latest versions of Pydantic AI. You must use the unified `MCPToolset` class to connect your agent to the Vinkius endpoint.

Pydantic AI will raise a validation error at runtime, stopping the agent from executing further. This prevents the agent from hallucinating flag states or proceeding with invalid configuration data.

Yes, the server must be hosted externally. Vinkius handles this by hosting the MCP Server in a secure, managed environment, providing a stable HTTP endpoint for your `MCPToolset`.

User traits processed by `identify_user` are validated in memory and sent over HTTPS. Vinkius runs the MCP Server inside an ephemeral V8 Isolate sandbox, ensuring no user data is cached or stored permanently on the host.

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