Bring Feature Flags
to Pydantic AI
Learn how to connect Statsig to Pydantic AI and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Statsig MCP Server?
Connect your Statsig project to any AI agent to manage feature rollouts and product experiments through natural conversation.
What you can do
- Feature Gates — Evaluate if a feature is enabled for a specific user or list all project gates
- Dynamic Configs — Fetch JSON configurations and experiments to control app behavior without code changes
- Event Logging — Log custom events for real-time analytics and metric calculation
- Gate Management — Create, update, or delete feature gates directly via the Console API
- Layer Inspection — Evaluate layers and retrieve parameter values for specific users
How it works
- Subscribe to this server
- Enter your Statsig Server Secret Key (for evaluation) and Console API Key (for management)
- Start managing your product experiments from Claude, Cursor, or any MCP client
Who is this for?
- Product Managers — check gate statuses and create new feature flags without leaving the chat
- Developers — verify evaluation logic and log test events directly from the IDE
- Data Scientists — inspect experiment configurations and verify metric logging
Built-in capabilities (12)
Requires STATSIG_SERVER_SECRET_KEY. Evaluates one or more feature gates for a user
Requires STATSIG_CONSOLE_API_KEY. Create a new dynamic config
Requires STATSIG_CONSOLE_API_KEY. Create a new feature gate
Requires STATSIG_CONSOLE_API_KEY. Delete a feature gate
Requires STATSIG_SERVER_SECRET_KEY. Fetches configuration values for a dynamic config or experiment
Requires STATSIG_CONSOLE_API_KEY. Read a specific dynamic config
Requires STATSIG_CONSOLE_API_KEY. Read a specific feature gate
Requires STATSIG_SERVER_SECRET_KEY. Fetches parameter values from a layer
Requires STATSIG_CONSOLE_API_KEY. List all dynamic configs in the project
Requires STATSIG_CONSOLE_API_KEY. List all feature gates in the project
Requires STATSIG_SERVER_SECRET_KEY. Logs custom events for analytics and metric calculation
Requires STATSIG_CONSOLE_API_KEY. Update an existing feature gate
Why Pydantic AI?
Pydantic AI validates every Statsig tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Statsig integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Statsig connection logic from agent behavior for testable, maintainable code
Statsig in Pydantic AI
Statsig and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Statsig to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Statsig in Pydantic AI
The Statsig MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Statsig for Pydantic AI
Every tool call from Pydantic AI to the Statsig MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
What is the difference between the Server Secret Key and the Console API Key?
The Server Secret Key is used for evaluation tools like check_gate and get_config. The Console API Key is required for management actions like list_gates or create_gate.
How do I evaluate a gate for a specific user?
Use the check_gate tool. You must provide the gateName and a user JSON object containing at least a userID (e.g., {"userID": "123"}).
Can I log custom events for analytics?
Yes, use the log_event tool to send an array of event objects including name, value, and user metadata to Statsig for real-time metric calculation.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Statsig MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Revolut Business
10 toolsGrant your AI access to Europe's powerhouse treasury. Automate multi-currency exchange, mass payouts and real-time vendor bulk-payments.
Radarr (Movies)
15 toolsManage your movie library, search for new titles, and monitor download queues via Radarr.
Vivo Game Open Platform
9 toolsManage Vivo Game Open Platform distribution — validate logins, query orders, and report game data directly from any AI agent.
Solcast Solar
11 toolsAccess solar irradiance and PV power forecasts — rooftop solar estimates, radiation data, and weather forecasts via Solcast API.