OrcA 0.3 lets you see exactly what your AI agent does with your MCP servers, without leaving VS Code. Chat with your servers using the model you already have, watch every LLM round and every MCP tool call in a live Git-style graph, and capture what GitHub Copilot or Claude send to your server. No telemetry, no extra app, no code changes.
Your API contracts live in your editor. Until today, your MCP servers lived somewhere else: a terminal running a CLI, a browser tab with a console, a dashboard for deployments, and a doc page you kept re-reading. OrcA MCP puts that whole journey in one place.
An AI agent can understand what a person means. It should not improvise how a production business process runs.
The architecture is simple:
AI interprets intent. APIs define the rules. Deterministic workflows execute approved outcomes.
A common problem in production happens when an agent can see many tools, but it still needs to know which action is appropriate now, what must happen first, and when it should stop and ask. The non-deterministic nature of AI agents makes this particularly challenging without structured guidance.
The HAPI Capability Graph and Capability Planning address this problem by providing structured guidance for the agent.
Every team adopting MCP eventually hits the same fork in the road: reimplement your business capabilities as an MCP server, or expose what you already have through one.
The first path feels faster on day one. It's also how a second, hidden application — a shadow of the one you already trust — gets built without anyone deciding to build it.
AI has dramatically reduced the cost of writing code. It has not reduced the cost of owning it.
That distinction may become one of the most important architecture lessons of the AI era.
Today, almost anyone inside an engineering organization can open an AI coding assistant and say:
"Here is my API. Build an MCP server for it."
If your tool server needs to interrupt the model to ask a question, ask why the question wasn't answerable before the call started.
MCP elicitation is a real, spec-defined capability, and it solves a real problem. It's also becoming a convenient place to hide a design problem instead of fixing it.
The expensive part of enterprise AI is often not the model. It is rebuilding what already works.
Many software companies have spent years, and sometimes decades, turning business rules, customer needs, operational lessons, security controls, and hard-won reliability into production APIs.
Then AI arrives, and the first instinct is often: We need to rebuild the platform for agents.