Commit graph transports-wg/proposals
Author SHA1 Message Date
Peter Alexander
915d234173 Tighten abstract wording 2026-06-05 15:19:33 -06:00
Peter Alexander
eeee857c29 Revise sessionless MCP SEP for formal proposal
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.
2026-06-05 15:19:33 -06:00
Peter Alexander
de6986245c Add open questions on validation, blast radius, and SDK migration 2026-06-05 15:19:33 -06:00
Peter Alexander
9071bebb94 Fix author GitHub handle 2026-06-05 15:19:33 -06:00
Peter Alexander
deb5ede72b SEP-XXXX: Sessionless MCP via Explicit State Handles
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.
2026-06-05 15:19:33 -06:00
Caitie McCaffrey
7716a238a6
Writeup of design question for 2322-MRTR (#24)
This is a write up of a design discussion on SEP 2322-MRTR and design decision

Should requests for more information (i.e. the IncompleteResult
response) be supported as a response type on to all ClientRequests, or
should it be limited to a subset of Client Requests?
2026-03-19 14:38:23 -07:00
Mark D. Roth
61819cab19
SEP-XXXX: Multi Round-Trip Requests (#12)
This is a draft SEP for Multi Round-Trip Requests (MRTR).

## Motivation and Context
See SEP for details.

## How Has This Been Tested?
Not tested yet, that will happen when we implement.

## Breaking Changes
See SEP for details.

## Types of changes
- [ ] Bug fix (non-breaking change which fixes an issue)
- [x] New feature (non-breaking change which adds functionality)
- [x] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update

## Checklist
- [x] I have read the [MCP
Documentation](https://modelcontextprotocol.io)
- [x] My code follows the repository's style guidelines
- [x] New and existing tests pass locally
- [x] I have added appropriate error handling
- [x] I have added or updated documentation as needed

## Additional context
N/A

---------

Co-authored-by: Caitie McCaffrey <caitiem20@github.com>
2026-03-02 11:36:17 -07:00
Mark D. Roth
1edadf9718
Multi Round-Trip Requests Track: Brief (#5)
Add the "Multi Round-Trip Requests" track briefing doc to the repo.

Note that there was some previous discussion in the [original
location](https://docs.google.com/document/d/1i12c1NXhDBaCQYlL-GOpC2fh6Yr_2itlc07WP7-JqAE/edit?usp=sharing).
2026-02-13 11:40:19 -08:00
Peter Alexander
a67f95ca0f
Initial repository structure for Transports WG
Set up the basic structure for the MCP Transports Working Group, modeled
after the financial-services-interest-group repository.

Files added:
- README.md: Mission, meetings, focus areas, participation guide
- CHARTER.md: Scope, proposal promotion pathway
- GOVERNANCE.md: Roles, decision-making process (maintainers TBD)
- CONTRIBUTING.md: How to participate and contribute
- LICENSE: MIT License
- docs/: Directory for future documentation
- proposals/: Directory for transport proposals/specs

Focus areas:
- Scalability (connection pooling, load distribution)
- Reliability (error handling, reconnection, delivery guarantees)
- Transport Semantics (protocol behavior, message ordering)
- Interoperability (cross-platform compatibility, testing)
2026-01-08 13:15:50 +00:00