How do I get an API Key for FullStory?

Log in to FullStory, navigate to Settings > API Keys, and click on 'Create Key' to generate a new token with Admin or Architect permissions.

What is the difference between ID and UID?

The 'id' is a system-generated unique identifier from FullStory, while the 'uid' is your application's own internal user ID passed via FS.identify.

Can I watch session playbacks through the agent?

The agent can retrieve the 'fsUrl' for any session, which is a direct link to watch the playback in your browser. You cannot watch the video inside the chat interface directly.

Are custom user properties supported?

Yes! When you use 'upsert_user' or 'get_user_details', all custom properties stored in the 'properties' object are accessible and manageable via the agent.

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

Name: FullStory
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 FullStory through the 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 FullStory "
            "(11 tools)."
        ),
    )

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

Connect your FullStory account to any AI agent to automate your digital experience intelligence (DXI) and product analytics workflows through the Model Context Protocol (MCP). FullStory provides a comprehensive view of how users interact with your site or app. This MCP server enables you to manage user profiles, track server-side events, and retrieve session metadata and playback links directly through natural conversation.

Pydantic AI validates every FullStory tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through the 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

User Lifecycle Management — List all captured users, fetch detailed profile metadata, and upsert records to maintain accurate identity mapping.
Session Oversight — Retrieve a list of recording sessions for specific users and access playback URLs to visualize the customer journey.
Interaction Events — Fetch the complete set of captured events (clicks, navigations, custom events) for any specific session ID.
Server-Side Tracking — Log custom interaction events programmatically from your backend to enrich your FullStory datasets.
Segment Discovery — Access and list configured user segments to understand high-level audience behavior.
Data Exports — Monitor and list generated raw data bundles for deeper analytical processing.
Privacy Compliance — Programmatically delete user data to support GDPR and CCPA requests via simple AI commands.

The FullStory 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 FullStory to Pydantic AI via MCP

Follow these steps to integrate the FullStory 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 FullStory with type-safe schemas

Why Use Pydantic AI with the FullStory MCP Server

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

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

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

FullStory + Pydantic AI Use Cases

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

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

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

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

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

FullStory MCP Tools for Pydantic AI (11)

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

create_event

Automatically mapped for server-side metrics injection that bypassed the frontal JavaScript client. Dispatch a custom backend event into FullStory

create_update_user

Used to synchronize custom tenant data into the FullStory analytics boundary for enhanced session context. Upsert a user identity into FullStory tracking

delete_user

Permanently removes privacy-sensitive telemetry, custom property links, and session aggregations inside FullStory. Erase a user profile and their associated session history

get_account_info

Validates live integration capability and fetches workspace scope definitions. Verify authentication and retrieve basic platform stats

get_session

Resolves page transitions, total active time, event markers, and active direct access tracking links. Retrieve deep metadata for a specific session recording

get_session_events

Exposes click trails, navigation mutations, error logs, and precise structural DOM changes. Fetch the chronological telemetry events for a session

get_user

Retrieves raw session metadata, total session durations, custom variables, and cross-device interaction boundaries. Get full tracking profile and behavior history for a specific user

list_exports

Resolves the status of bulk data offloads, processing states, and download URIs for warehouse ingestion. List raw data export jobs available for download

list_segments

Resolves saved audience definitions, population counts across the last 30 days, and logical filter structures. List dynamic audience segments built in FullStory

list_sessions

Resolves a subset of sessions matching provided JSON query criteria, exposing playback links, browser signatures, and metric overlays. List or search session recordings based on telemetry

list_users

Resolves user identities, custom parameters, session counts, and aggregate behavioral profiles across the analytics boundary. Query the FullStory subscriber and visitor directory for analytics

Example Prompts for FullStory in Pydantic AI

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

"List the last 5 sessions for user UID 'user_12345'."

"Show me the full profile details for FullStory ID '123:456'."

"Track a server event 'Subscription Renewed' for user 'johndoe@email.com'."

Troubleshooting FullStory MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

FullStory + Pydantic AI FAQ

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