How do I get my Appcues API Key and Secret?

You can generate API keys in the Appcues Studio. Go to **Settings > Integrations > API Keys** to create a new set of credentials.

What is my Appcues Account ID?

Your Account ID is a unique numeric identifier for your Appcues account. You can find it in the URL of your Appcues Studio (e.g., studio.appcues.com/accounts/YOUR_ID) or in your Account Settings.

Does this server support the EU region?

Yes, you can configure the `APPCUES_REGION` environment variable to `eu` if your account is hosted in the Appcues European data center.

Appcues MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: Appcues
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Appcues 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 Appcues "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Appcues?"
    )
    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 Appcues MCP Server

The Appcues MCP Server empowers your AI agent to interact directly with your Appcues account. Whether you need to audit your current onboarding flows, manage user segments, or track real-time user activity, this integration provides a seamless natural language interface to your product experience platform.

Pydantic AI validates every Appcues tool response against typed schemas, catching data inconsistencies at build time. Connect 11 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.

Key Features

Flow Management — List, view, publish, and unpublish flows (in-app experiences) across web and mobile.
User Segmentation — Retrieve and analyze your targeting segments to understand who is seeing your content.
Activity Tracking — Send real-time events and profile updates for immediate targeting and personalization.
Mobile Support — Access specific experiences designed for your mobile applications.
Auditing & Reporting — Quickly check account status, checklists, and experience metadata.

Benefits for Teams

Product Managers — Quickly audit which onboarding flows are active and make changes without leaving your AI workspace.
Growth Engineers — Programmatically track user events to trigger personalized in-app journeys.
Customer Success — View user profiles and segment membership to provide better support and guidance.

The Appcues MCP Server exposes 11 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 Appcues to Pydantic AI via MCP

Follow these steps to integrate the Appcues 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 11 tools from Appcues with type-safe schemas

Why Use Pydantic AI with the Appcues MCP Server

Pydantic AI provides unique advantages when paired with Appcues 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 Appcues integration code

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

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

Appcues + Pydantic AI Use Cases

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

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

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

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

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

Appcues MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect Appcues to Pydantic AI via MCP:

get_account_details

Verify Appcues account connection

get_flow

Get details for a specific flow

get_segment

Get details for a specific segment

get_user_profile

Retrieve the profile of a specific user

list_checklists

List all checklists configured in the account

list_flows

List all Appcues flows (experiences) for the account

list_mobile_experiences

List mobile-specific experiences

list_segments

List all user segments defined in Appcues

publish_flow

Publish a draft flow

track_user_activity

Use JSON strings for profileUpdate and events. Track real-time events and profile updates for a user

unpublish_flow

Unpublish an active flow

Example Prompts for Appcues in Pydantic AI

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

"List all my active Appcues flows."

"Track a 'clicked_checkout' event for user 'user_123'."

"Show me the details of the segment with ID '998877'."

Troubleshooting Appcues MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Appcues + Pydantic AI FAQ

Common questions about integrating Appcues 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 Appcues MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.