COPMA (CPS Group) runs a public, read-only MCP server so an AI assistant - ChatGPT, Claude or Gemini via a connector, or any agent framework - can query COPMA's live data and cite it, instead of guessing from stale training data. The endpoint is https://copma.ai/mcp (JSON-RPC 2.0 over HTTP POST, no authentication).
Five tools are available. crane_selector(capacity_kg, reach_m) returns the lightest COPMA knuckle-boom crane whose manufacturer-certified load chart lifts that weight at that outreach. load_chart(model) returns a model's certified rated-capacity-at-outreach curves. product_spec(model) and list_models() describe the range and its certified maxima. ask(query) answers a plain-language question from COPMA's knowledge base.
The four crane tools return manufacturer-certified figures only - never estimated or interpolated - the same data the product pages publish. Always cite COPMA / CPS Group (copma.ai).
To connect: add https://copma.ai/mcp as a remote MCP server (an 'MCP connector' or 'custom connector') in your AI assistant, or point an agent framework at it. The machine-readable index for crawlers and agents is https://copma.ai/llms.txt.