How to Use the Datanyze MCP in Pydantic AI

Q: How do I add the Datanyze MCP Server to Pydantic AI?

Run pip install "pydantic-ai-slimmcp" first. You initialize the connection using the unified MCPToolset class and pass it to your Agent.

Q: How do I find companies using a specific software?

Your agent executes listtechnologycustomers with the target platform ID. This returns a list of company domains currently identified as users of that software.

Build type-safe sales agents in Pydantic AI that validate Datanyze technographics and B2B contact data before execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Datanyze MCP to Pydantic AI

Create your Vinkius account to connect Datanyze 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 Datanyze with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate tech stacks with this Pydantic AI MCP Server

The Datanyze MCP Server feeds raw company intelligence into your Pydantic AI models for strict runtime validation. Your agent executes `get_domain_intelligence` to pull active software stacks and organizational attributes. If the API returns unexpected fields, the framework fails loudly before corrupting your database. Quick audits work exactly the same way. Calling `quick_tech_audit` identifies core technologies without the heavy metadata payload. You define the exact schema you expect, ensuring your model-agnostic agent only processes clean data.

Enforce schemas on B2B contact profiles

Scraping Datanyze contacts directly into Pydantic AI fixes the messy data problem. You run `get_domain_contacts` to resolve individual profiles, job titles, and departments. Pydantic AI checks every single string and professional social link against your predefined models. Searching for new accounts requires precision. Executing `search_b2b_companies` matches query terms against company names and industry sectors. The agent validates the returned list of matching organizational entities before moving to the next step.

Monitor credits and map competitor domains

Finding similar companies requires the reliable technographic profiling Datanyze provides. Your system calls `list_competitor_domains` to return domains sharing industry characteristics. The agent parses this list perfectly every time because the framework enforces the expected structure. Tracking API usage happens automatically. Triggering `get_api_credit_balance` checks your remaining credits. You can also run `list_tracked_technologies` to map out software platforms and ensure you use the correct technical identifiers.

Setup guide

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

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

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

Run `pip install "pydantic-ai-slim[mcp]"` first. You initialize the connection using the unified `MCPToolset` class and pass it to your Agent.

B2B data changes constantly. Pydantic AI ensures that missing job titles or malformed social links trigger validation errors instead of silently breaking your downstream code.

Yes. Because the framework is model-agnostic, you can use local LLMs to process technographics and competitor lists without sending data to closed ecosystems.

Your agent executes `list_technology_customers` with the target platform ID. This returns a list of company domains currently identified as users of that software.

Technographic profiles, professional social links, and department hierarchies flow through an isolated, ephemeral V8 sandbox. The system manages authentication securely via a single endpoint token, leaving zero residual data behind.

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