Skip to main content

​
Why ECP

ECP (Execution Control Protocol) fills the execution layer between tool calling and production agent systems. If MCP standardizes how AI systems call tools, ECP standardizes how AI systems run: portable workflows, governed environments, policies, and host runtimes.

​
The problem

As agents move from prototypes to production:
  • Tool permissions become unclear
  • Actions are hard to audit
  • Context and mounts are inconsistent
  • Execution environments are not reproducible
  • Governance is bolted on after the fact
Teams solve this with one-off orchestration code. There is no shared way to package “how this agent runs here.”

​
What ECP gives you

  • Workflows — versioned, portable graphs (Fluent/TS or JSON)
  • Environments — runtime + extensions + policies that bind a host
  • Deterministic ops — validate, describe, search, encode, decode, patch, run
  • Hosts — Node CLI, browser runtime, MCP adapter
  • Composability — same operational APIs after env.init(), regardless of host
ECP is not another agent framework or chat UI. It is infrastructure for governed execution.

​
Next steps