modelcontextprotocol/transports-wg
Watch
1
0
Fork
You've already forked transports-wg
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Tighten abstract wording

Browse source
This commit is contained in:
Peter Alexander 2026-04-14 13:24:40 +01:00 • committed by Kurtis Van Gent
commit 915d234173
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
proposals/XXXX-sessionless-mcp.md
View file

@ -12,9 +12,9 @@
This proposal removes the protocol-level session concept from MCP, replacing implicit session-scoped state with explicit, server-minted state handles that the model carries and threads through subsequent calls. [SEP-1442] makes sessions optional by defaulting to stateless operation; this proposal removes the opt-in as well.
After more than a year in the spec, sessions have not converged on a consistent meaning across clients: some scope them per tool call, some per application launch, some per page load, and almost none resume them. A server author cannot predict what scope or lifetime a session will have when their server is connected to an arbitrary client, which has made the session unreliable as a container for application state. This proposal holds that the known uses of session scoping — application state, mutable tool lists, and resource subscriptions — can each be served by explicit identifiers, and that the session abstraction adds constraints (fixed cardinality, undefined lifetime, uncacheable list endpoints) without corresponding benefit.
After more than a year in the spec, sessions have not converged on a consistent meaning across clients: some scope them per tool call, some per application launch, some per page load, and almost none resume them. A server author cannot predict what scope or lifetime a session will have when their server is connected to an arbitrary client, which has made the session unreliable as a container for application state. This proposal holds that application state can be served by explicit identifiers, and that the session abstraction adds constraints (fixed cardinality, undefined lifetime, uncacheable list endpoints across session boundaries) without corresponding benefit.
Under this proposal, a server that currently scopes a shopping cart (for example) to the session instead exposes a tool `create_basket()` that returns a `basket_id` and threads that id through subsequent tool calls, e.g. `add_item(basket_id, ...)`. The model decides what is shared and what is isolated; list endpoints become cacheable across what used to be session boundaries; and agent orchestrators can freely share or not share application state as needed. Explicit state handles are not a new protocol construct — there is no schema or wire format for them. They are a tool-design pattern; the protocol change is the removal of sessions, which leaves handles as the way to express cross-call state.
Under this proposal, a server that currently scopes a shopping cart (for example) to the session instead exposes a tool `create_basket()` that returns a `basket_id` and threads that ID through subsequent tool calls, e.g. `add_item(basket_id, ...)`. The model decides what is shared and what is isolated; list endpoints become cacheable across what used to be session boundaries; and agent orchestrators can freely share or not share application state as needed. Explicit state handles are not a new protocol construct — there is no schema or wire format for them. They are a tool-design pattern; the protocol change is the removal of sessions, which leaves handles as the way to express cross-call state.
[SEP-1442]: https://github.com/modelcontextprotocol/modelcontextprotocol/issues/1442
[SEP-2322]: https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2322