How to Use the Appcues MCP in Pydantic AI

Q: How do I connect Appcues to Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to your Vinkius URL and add it to your Agent's toolsets list.

Q: Can Pydantic AI track custom Appcues events?

Yes. The trackuseractivity tool accepts JSON strings for events. Pydantic AI ensures your agent formats this payload exactly as your schema dictates before sending it.

Q: How does Pydantic AI read Appcues segments?

The agent executes listsegments to get the directory and getsegment for specific rules. If the returned data structure changes, the framework throws a validation error immediately.

Connect Appcues to Pydantic AI to manage flows and track user events with strict runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Appcues MCP to Pydantic AI

Create your Vinkius account to connect Appcues 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 Appcues with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Appcues flows with Pydantic AI

Your agent pulls the current state of your product tours using `list_flows` to manage customer onboarding. You cannot afford silent failures when modifying user experiences. Pydantic AI strictly validates the returned JSON from `get_flow` against your predefined models. If the Appcues API returns an unexpected schema, the agent fails loudly. This guarantees your system never tries to execute `publish_flow` or `unpublish_flow` on a hallucinated ID. You get absolute certainty before altering live tooltips.

Push type-safe events via MCP Server

Your agent uses `track_user_activity` to send custom events and profile updates to Appcues. Logging backend actions requires precise formatting. Because you define the exact shape of the payload in Pydantic, the agent cannot send malformed JSON strings. Before pushing an update, the agent checks the existing record with `get_user_profile`. This read operation is also validated at runtime. Local models and hosted providers both maintain this perfectly rigid data structure.

Audit segments and checklists

The agent runs `list_segments` to fetch your audience definitions and understand who sees your messages. It calls `get_segment` for the exact rules. Every field, from user properties to behavioral triggers, is parsed into a strict Python object. You can audit other growth channels safely. The agent pulls `list_checklists` for web onboarding steps and `list_mobile_experiences` for iOS or Android campaigns. The MCP Server handles the transport, while your framework ensures the data is flawless.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` pointing to your Vinkius URL and add it to your Agent's `toolsets` list.

Yes. The `track_user_activity` tool accepts JSON strings for events. Pydantic AI ensures your agent formats this payload exactly as your schema dictates before sending it.

The agent executes `list_segments` to get the directory and `get_segment` for specific rules. If the returned data structure changes, the framework throws a validation error immediately.

It does. The server exposes the tools through the standard protocol. Your local model can call `list_flows` or `publish_flow` just like a hosted provider would.

We route all traffic through an ephemeral, zero-trust sandbox. When your agent fetches audience rules via `get_segment`, the data is processed in isolated memory. Vinkius never caches or stores your targeting logic.

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