#mcp
mcp shows up across 4 section(s) and 7 page(s) in this workspace. Use this page as a topic map, not just an archive.
Start here
If you are new to this topic, begin with the strongest entry points first, then move into related notes and supporting material.
- From Agent Intent to Governed Execution Systems
- Runtime Over Model: Why Orchestration Is the Product Systems
- Model proposes, runtime decides. Sentences
- Trace before trust. Sentences
Where it appears
- Systems 2 page(s)
- Sentences 3 page(s)
- Shelf 1 page(s)
- Sticky Notes 1 page(s)
From Agent Intent to Governed Execution
How an agent request becomes controlled system behavior through runtime orchestration, policy gates, verification, and traceability.
Runtime Over Model: Why Orchestration Is the Product
Reliable agents come from controlled execution loops, not model capability alone.
Model proposes, runtime decides.
Trace before trust.
Verification turns output into evidence.
Soothsayer MCP kernel: from prompts to controlled orchestration
How I built a policy-governed MCP runtime where models can reason freely but execution stays deterministic, verifiable, and auditable.