Where do I find my Personal Access Token?

In Optimizely, go to **Profile Settings** > **API Access** and generate a new Personal Access Token. Ensure it has the necessary permissions for the projects you want to manage.

Can I start an experiment that is in draft mode?

Yes, using the `start_experiment` tool will attempt to set the status to 'running'. However, Optimizely requires the experiment to be valid and fully configured before it can transition from draft to running.

How do I find my Project ID?

You can use the `list_projects` tool to see all projects associated with your account along with their IDs. You can also find it in the URL when viewing a project in the Optimizely dashboard.

Optimizely MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Optimizely
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Optimizely through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Optimizely "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Optimizely?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About Optimizely MCP Server

Connect your Optimizely account to any AI agent and take full control of your experimentation and feature management workflows through natural conversation.

Pydantic AI validates every Optimizely tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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.

What you can do

Project Overview — List all projects and retrieve detailed metadata to maintain a clear view of your workspace.
Experiment Management — List experiments, check current status (running, paused, draft), and retrieve detailed configurations.
Feature Flag Tracking — List feature flags and inspect their definitions across different projects.
Audience & Event Auditing — List defined audiences and conversion events to verify your targeting and tracking setup.
Live Controls — Start or pause experiments directly through the agent to react quickly to results or issues.

The Optimizely MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Optimizely to Pydantic AI via MCP

Follow these steps to integrate the Optimizely MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Optimizely with type-safe schemas

Why Use Pydantic AI with the Optimizely MCP Server

Pydantic AI provides unique advantages when paired with Optimizely through the Model Context Protocol.

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 Optimizely integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Optimizely connection logic from agent behavior for testable, maintainable code

Optimizely + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Optimizely MCP Server delivers measurable value.

Type-safe data pipelines: query Optimizely with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Optimizely tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Optimizely and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Optimizely responses and write comprehensive agent tests

Optimizely MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Optimizely to Pydantic AI via MCP:

get_experiment

Get details for a specific experiment

get_feature_flag

Get details for a specific feature flag

get_project

Get details for a specific project

list_audiences

List defined audiences in a project

list_events

List conversion events in a project

list_experiments

List experiments in a project

list_feature_flags

List feature flags in a project

list_projects

List all Optimizely projects

pause_experiment

Set experiment status to paused

start_experiment

Set experiment status to running

Example Prompts for Optimizely in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Optimizely immediately.

"List all Optimizely projects in my account."

"Check the status of all experiments in project 12345."

"Pause experiment 67890 in project 12345."

Troubleshooting Optimizely MCP Server with Pydantic AI

Common issues when connecting Optimizely to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Optimizely + Pydantic AI FAQ

Common questions about integrating Optimizely MCP Server with Pydantic AI.

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 Optimizely MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.