How to Use the CB Insights MCP in Pydantic AI

Q: What's the setup for adding the CB Insights toolset to a Pydantic AI agent?

After pip install "pydantic-ai-slimmcp", you create an instance of MCPToolset("http://...") with your Vinkius server URL. Then you pass it into the toolsets list when you create your Agent.

Get type-safe, validated CB Insights data in your Pydantic AI agent. No silent data corruption, just correct market intelligence.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CB Insights MCP to Pydantic AI

Create your Vinkius account to connect CB Insights 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 CB Insights with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guaranteed Data Structures

Use `get_organization` or `get_deal` and let Pydantic AI do the work. Every response from the CB Insights server is automatically validated against Pydantic models at runtime. If the API ever returns an unexpected field or a wrong data type, your agent doesn't guess or corrupt data. It fails loudly with a `ValidationError`, so you know immediately that something is wrong. This is about correctness, not just convenience.

Use Any LLM with This MCP Server

Pydantic AI is model-agnostic. You can use OpenAI, Anthropic, Gemini, or a local model to drive your agent's logic. The CB Insights toolset works the same way regardless of the brain you plug in. This means you can build your agent to use `list_investors` and `get_investor_portfolio`, test it with a cheap model, and then swap in a more powerful one for production without changing a single line of your tool-calling code.

A Single Toolset for All CB Insights Tools

The `MCPToolset` gives you a clean way to add all 13 CB Insights tools to your agent. Just point it at the Vinkius URL and pass it to your `Agent` constructor. This unified approach is simple and future-proof. You get access to everything from `chat_cbi` for conversational queries to `list_deals_by_org` for specific lookups, all managed through one object.

Setup guide

Set up CB Insights 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": {
        "cb-insights-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

It validates every API response from the CB Insights MCP server against Pydantic models. If a deal record is missing a field or an investor ID is formatted incorrectly, Pydantic AI will raise a `ValidationError` instead of letting your agent work with bad data.

Yes. Pydantic AI is model-agnostic. You can connect the CB Insights `MCPToolset` to an agent running a local model just as easily as one running on OpenAI or Gemini.

After `pip install "pydantic-ai-slim[mcp]"`, you create an instance of `MCPToolset("http://...")` with your Vinkius server URL. Then you pass it into the `toolsets` list when you create your `Agent`.

No. The MCP server provides the schema. Pydantic AI uses this schema to dynamically handle validation for you. You just call the tools and trust that the data you get back is structured correctly.

Your data's security is handled at the transport layer. Your agent's requests for funding, competitor, and organization data are sent over HTTPS to the Vinkius MCP Server, which runs in a sandboxed environment and requires a unique token for access. The data is proxied, not stored.

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