Reframe to argue against sessions as a concept rather than against a
hypothetical opt-in alternative. Add citations for real-world client
session behavior, an ecosystem impact survey, concrete server examples
(Linear/Notion/GitHub/Stripe), and references to SEP-2322 and SEP-2549.
Clarify that explicit handles are a design pattern with no protocol
surface, address request-ID and pagination-cursor re-scoping, and tighten
tone throughout. Remove open questions, follow-on sections, and the
comparison table.
Add draft proposal to remove the protocol-level session concept from MCP
entirely, replacing implicit session-scoped state with explicit,
server-minted state handles that the model threads through subsequent
calls.
Key arguments:
- Session lifetime is undefined and server authors cannot design around it
- List endpoints cannot be cached across sessions, forcing O(subagents ×
servers) re-fetches even when tool sets never change
- Session cardinality is fixed at exactly one, preventing mixed
shared/isolated state in subagent fan-out patterns
- Explicit handles are strictly more expressive: anything expressible
with a session is expressible with a single ID created up front
Builds on SEP-1442 (stateless-by-default) but goes further by asking
whether the opt-in stateful path needs to exist at all.