How to Use the CompanyCam MCP in Pydantic AI

Q: How do I initialize the CompanyCam MCP Server toolset in Pydantic AI?

Use the MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset instance into the toolsets argument of your Pydantic AI agent to register all ten construction tools.

Q: Does the Pydantic AI integration support the deprecated HTTP classes?

No, you should avoid the deprecated MCPServerHTTP class. Use the unified MCPToolset approach instead to connect your agent to the server.

Build type-safe construction agents with Pydantic AI and the CompanyCam MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CompanyCam MCP to Pydantic AI

Create your Vinkius account to connect CompanyCam 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 CompanyCam with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Photo and Project Management

This MCP Server provides `list_project_photos` and `get_photo_details` with strict schema definitions that Pydantic AI validates at runtime. If the API returns a photo record with missing fields, the framework catches it immediately before your agent processes it. This strict validation prevents silent failures in your production pipelines. Your agent can confidently extract image URLs and metadata, knowing the data matches your exact Python models.

Validate Project Creation Schemas

The `create_project` tool allows your agent to generate new records in CompanyCam with strict input validation. Pydantic AI checks the project parameters against your defined schemas before sending the request to the server. Here is the thing: if your agent tries to supply an invalid project name or bad metadata, the call fails loudly. This guarantees that your CompanyCam account stays clean and free of malformed project records.

Structured Document and User Queries

The `list_project_documents` and `search_projects` tools return structured lists that parse cleanly into Pydantic models. Your agent can search for a project and immediately verify its documents and assigned staff via `list_users`. Because Pydantic AI is model-agnostic, you can use these validated tool outputs with OpenAI, Anthropic, or local models. The framework handles the parsing layer so your agent code stays clean and predictable.

Setup guide

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

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

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

Use the `MCPToolset` class pointing to your Vinkius HTTP endpoint. Pass this toolset instance into the `toolsets` argument of your Pydantic AI agent to register all ten construction tools.

The framework will raise a validation error immediately. This prevents your agent from making decisions based on corrupted or incomplete photo and project payloads.

No, you should avoid the deprecated `MCPServerHTTP` class. Use the unified `MCPToolset` approach instead to connect your agent to the server.

Yes, Pydantic AI is model-agnostic. You can back your agent with a local model or a commercial API while using this server to fetch construction data.

Vinkius runs the server in a secure, ephemeral V8 sandbox. Your construction documents, user lists, and photo metadata are processed in-memory and never cached or stored on Vinkius servers.

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