How to Use the CompanyCam MCP in OpenAI Agents SDK

Q: Does the OpenAI Agents SDK support caching for CompanyCam tools?

Yes, you should set cacheToolsList=True in your connection parameters. This prevents the SDK from repeatedly querying the endpoint for tools like listprojects and listallphotos, reducing latency.

Q: How do I trace CompanyCam API calls made by the agent?

Every tool invocation, from getproject to document retrieval, is recorded in your OpenAI dashboard. This gives you complete visibility into which agent ran which tool and what data was returned.

Feed live jobsite photos and construction project data directly to your OpenAI Agents SDK pipelines with zero-config tool discovery.

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 OpenAI Agents SDK

Create your Vinkius account to connect CompanyCam to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync Jobsite Photos with OpenAI Agents SDK

This MCP Server exposes `list_project_photos` and `get_photo_details` so your OpenAI Agents SDK can inspect construction images directly. The agent uses these tools to pull raw visual assets, check timestamps, and match them to specific field issues. Because the SDK supports built-in guardrails, you can intercept these tool calls before they execute. This lets your system verify that an agent does not pull photos from restricted projects or request details for unauthorized image IDs.

Manage Projects Safely via Guardrails

The `create_project` tool lets your agent spin up new CompanyCam workspaces on the fly. Instead of writing custom boilerplate, the OpenAI Agents SDK auto-discovers this tool and makes it available to your specialized coordinator agents. You can track every single project creation request directly inside your OpenAI dashboard. If an agent tries to call `search_projects` to find a customer record, the execution is fully logged and traced for audit compliance.

Document Retrieval and User Mapping

The `list_project_documents` tool connects your agent to blueprints, permits, and change orders. Combined with `get_current_user` and `list_users`, the agent can attribute document updates to specific field technicians. This MCP Server setup shines when you need to hand off tasks between specialized agents. One agent can find the files, while another uses the user lists to assign follow-up tasks to the right estimator.

Setup guide

Set up CompanyCam MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CompanyCam tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CompanyCam tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CompanyCam tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CompanyCam Agent",
            instructions="You have access to CompanyCam tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK via pip, then initialize the server using the `MCPServerStreamableHttp` class with your Vinkius endpoint. Pass the server instance directly into the Agent constructor's `mcp_servers` list to enable auto-discovery.

Yes, you can enforce this through the SDK's native guardrails or by using specialized agents that only have access to specific tool lists. This prevents unauthorized calls to tools like `create_project`.

Yes, you should set `cacheToolsList=True` in your connection parameters. This prevents the SDK from repeatedly querying the endpoint for tools like `list_projects` and `list_all_photos`, reducing latency.

Every tool invocation, from `get_project` to document retrieval, is recorded in your OpenAI dashboard. This gives you complete visibility into which agent ran which tool and what data was returned.

Vinkius runs this MCP Server in an isolated V8 sandbox, ensuring your jobsite photos, blueprints, and user directories are never stored. The connection uses ephemeral instances that process the API payload and immediately discard the session data.

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