MCPL is a backward-compatible extension to the Model Context Protocol (MCP) that enables servers to be active participants in the inference lifecycle.
- Push Events — Servers can push events to hosts that may trigger model inference
- Context Hooks — Servers can inject or modify context before and after inference
- Server-Initiated Inference — Servers can request autonomous inference from the host
- Feature Sets — Fine-grained access control for server behaviors
- Scoped Access — Granular permission control within feature sets
See SPEC.md for the full protocol specification.
Draft specification (v0.4.1-draft). Subject to change.
MIT