How to Use the Harmonic MCP in Pydantic AI

Q: What happens if Harmonic's API returns data that doesn't match the schema for Pydantic AI?

Your agent will fail loudly and immediately with a ValidationError. This is a feature, not a bug. It prevents your agent from making decisions based on incomplete or corrupted data, which is essential for building dependable applications.

Q: How do I get an investor's portfolio with Harmonic and Pydantic AI?

Your agent just needs to call the getinvestorportfolio tool with the investor's name or ID. The response, which is a list of their portfolio companies, will be automatically parsed into a list of Pydantic models for you.

Get type-safe startup intelligence for your Pydantic AI agent. If the data's not right, your agent will know.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harmonic MCP to Pydantic AI

Create your Vinkius account to connect Harmonic 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 Harmonic with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Every Data Point

The `enrich_company` and `enrich_person` tools give your agent deep insights. But with Pydantic AI, it's about more than just getting the data. It's about knowing the data is correct. Every response from Harmonic is automatically parsed and validated against your Pydantic models. If the API ever returns an unexpected field or a wrong data type, your code stops with a clear `ValidationError`. No silent data corruption. No guessing games. This makes your agent's data handling predictable and safe.

Model-Agnostic Intelligence

The `search_startups` tool lets you find new companies. With Pydantic AI, you can power this search with any LLM you want — OpenAI, Anthropic, Gemini, or even a local model running on your own machine. The Harmonic toolset doesn't care. Your agent's logic for calling the tool and handling the response stays the same. The Pydantic AI framework and this MCP server provide a stable interface, so you can swap out the underlying language model without rewriting your data-fetching code.

Build Correct Data Pipelines with Pydantic AI

Use `list_funding_rounds` or `get_company_stats` to pull structured financial and growth data. Because you're using Pydantic AI, you have a guarantee that the data your agent receives matches the schema you've defined in your code. This is critical for building reliable systems. You can confidently take the output from your agent and feed it into a database, another API, or a reporting dashboard. The validation happens at runtime, ensuring data integrity from end to end.

Setup guide

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

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

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

It validates every API response against a Pydantic model at runtime. If the data from a tool like `list_funding_rounds` doesn't perfectly match the expected structure and types, Pydantic AI will raise a `ValidationError` instead of letting your agent use bad data.

Yes. Pydantic AI is model-agnostic. You can run a local model and connect it to the Harmonic MCP server to enrich a list of company domains without your data ever leaving your control, aside from the call to the Harmonic API itself.

Your agent will fail loudly and immediately with a `ValidationError`. This is a feature, not a bug. It prevents your agent from making decisions based on incomplete or corrupted data, which is essential for building dependable applications.

Your agent just needs to call the `get_investor_portfolio` tool with the investor's name or ID. The response, which is a list of their portfolio companies, will be automatically parsed into a list of Pydantic models for you.

This server handles inputs like company domains and person URLs to fetch professional history. Each tool call your agent makes is executed within a fresh, ephemeral container on the Vinkius platform. Once the job is done, the container and all its memory are destroyed, ensuring no data persists.

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