How to Use the Mattermark MCP in Pydantic AI

Validate your startup research with Pydantic AI and ensure strict data integrity for every Mattermark query.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mattermark MCP to Pydantic AI

Create your Vinkius account to connect Mattermark 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 Mattermark with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe startup research with Pydantic AI

Every response from `get_company_details` is validated against Pydantic models at runtime. If the API returns malformed data, your agent stops immediately, preventing silent failures. This is essential for high-stakes investment analysis. You define the schema, and the framework enforces it, ensuring your agent works with clean, predictable data.

Runtime data integrity verification

Your agents operate with a high degree of certainty. When calling `get_funding_round_details`, the result must match your expected structure or the agent raises a validation error. This approach removes the risk of hallucinated fields. You get a reliable data pipeline that works with any model, whether you're using OpenAI, Anthropic, or local LLMs.

Modular toolset management

Add the Mattermark tools to your agent with a single `MCPToolset` implementation. You can mix and match these tools with your internal logic to build specialized research agents. Use `search_companies` to trigger follow-up calls to `get_company_news`. The type-safety guarantees that the data passed between these calls remains consistent throughout the entire operation.

Setup guide

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

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

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

You define your Pydantic models, and the framework automatically validates the tool output against them. Any mismatch triggers an immediate error.

Yes, it’s the only way to guarantee that your agent logic doesn't break when the API data shifts. It forces the agent to handle reality, not assumptions.

Absolutely. The toolset is model-agnostic, letting you pair Mattermark data with whatever LLM you have running locally.

You connect via Streamable HTTP or SSE. The server runs as an external process, keeping your agent code lightweight and focused.

Data is validated locally within your runtime environment. The server only transmits the specific company and investor identifiers you authorize.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python