Muthukrishnan Bommiah · muthub.org
The open prototype at aac.muthub.org, described in its own notation and validated by its own rules. A level-by-level C4 walkthrough of the design decisions that mattered, and what I would change before an enterprise ran it.
Governed AI7 min readAs agents multiply, every enterprise needs an authoritative directory of the tools they can call. What a governed MCP registry must do, what the official registry leaves to you, and the mistakes to avoid.
Governed AI5 min readAgents act on their own, at machine speed, across many systems. Static credentials and perimeter thinking don't hold up. Attested identity, explicit delegation and policy enforced outside the model do.
Governed AI5 min readThe Model Context Protocol standardizes how agents connect to tools and data. It is silent on whether they should. Four risk areas a regulated institution should resolve before agents get tools.
Governed AI6 min readMCP ended the copy-paste problem with three simple primitives. Being open is why it beat a thousand bespoke integrations.
Note1 min readDirect remote MCP access through the Messages API removed a client layer and moved agent integration from clever hacks toward engineering.
Note1 min readMCP connects agents to tools; Agent2Agent connects agents to each other. Together they turn single agents into systems, and raise the governance stakes.
Note1 min readOAuth 2.1 authorization, streamable HTTP, batching and tool annotations: the March 2025 update that made enterprise MCP plausible.
Note1 min read