How do I find my TA Project APPID and Tokens?

Log in to your [ThinkingAnalytics Console](https://www.thinkingdata.cn/), go to [Project Management] -> [Project Info] to find your APPID and Data Token. The Query Secret is usually found in the [Account Management] or [API Management] section.

What is the 'distinctId'?

The `distinctId` is the unique identifier for a user in your system (e.g., a device ID or an account ID). It is used to tie events and properties to a specific individual profile in ThinkingAnalytics.

Can I perform complex data analysis through the agent?

Yes! Use the `query_events` tool with a JSON query definition. Your agent will fetch the raw or aggregated results from TA, allowing you to audit behavioral patterns using natural language reasoning over the returned data.

ThinkingData / 数数科技 MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: ThinkingData / 数数科技
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect ThinkingData / 数数科技 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 ThinkingData / 数数科技 "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in ThinkingData / 数数科技?"
    )
    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 ThinkingData / 数数科技 MCP Server

Empower your AI agent to orchestrate your data analytics and player insights with ThinkingData (数数科技), the premier analytics platform for the global gaming industry. By connecting ThinkingData to your agent, you transform complex event querying, user profile auditing, and cohort management into a natural conversation. Your agent can instantly retrieve project metadata, list defined events and their schemas, execute complex behavioral queries, and even ingest custom events without you ever needing to navigate the comprehensive TA Dashboard. Whether you are conducting a player retention audit or coordinating a live-ops event refresh, your agent acts as a real-time data coordinator, providing accurate results from a single, authorized source.

Pydantic AI validates every ThinkingData / 数数科技 tool response against typed schemas, catching data inconsistencies at build time. Connect 8 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.

What you can do

Project Orchestration — Retrieve project summaries, list defined events, and discover property schemas.
Behavioral Auditing — Execute complex queries on event data to understand player behavior and conversion funnels.
User Management — Query user profile data and update properties for specific distinct IDs.
Data Ingestion — Track custom events and set user properties directly through the agent for rapid testing.
Operational Insights — List defined user cohorts, saved reports, and monitor API connectivity status.

The ThinkingData / 数数科技 MCP Server exposes 8 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 ThinkingData / 数数科技 to Pydantic AI via MCP

Follow these steps to integrate the ThinkingData / 数数科技 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 8 tools from ThinkingData / 数数科技 with type-safe schemas

Why Use Pydantic AI with the ThinkingData / 数数科技 MCP Server

Pydantic AI provides unique advantages when paired with ThinkingData / 数数科技 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 ThinkingData / 数数科技 integration code

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

Dependency injection system cleanly separates your ThinkingData / 数数科技 connection logic from agent behavior for testable, maintainable code

ThinkingData / 数数科技 + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the ThinkingData / 数数科技 MCP Server delivers measurable value.

Type-safe data pipelines: query ThinkingData / 数数科技 with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple ThinkingData / 数数科技 tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query ThinkingData / 数数科技 and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock ThinkingData / 数数科技 responses and write comprehensive agent tests

ThinkingData / 数数科技 MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect ThinkingData / 数数科技 to Pydantic AI via MCP:

get_event_properties

Get properties for event

get_project_summary

Get project overview

list_defined_events

List project events

list_project_cohorts

List user cohorts

query_events

Execute event query

query_users

Execute user query

set_user_properties

Update user profile

track_custom_event

Track a single event

Example Prompts for ThinkingData / 数数科技 in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with ThinkingData / 数数科技 immediately.

"Show me a summary of our ThinkingData project configuration."

"List all defined events in ThinkingData."

"Check the profile for user 'USER_88210934'."

Troubleshooting ThinkingData / 数数科技 MCP Server with Pydantic AI

Common issues when connecting ThinkingData / 数数科技 to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

ThinkingData / 数数科技 + Pydantic AI FAQ

Common questions about integrating ThinkingData / 数数科技 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 ThinkingData / 数数科技 MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.