[Enh]: Support MCP protocol revision 2026-07-28 (stateless transport, server/discover, cacheable lists)
まだ誰も着手していません。
評価
調査の方向性
MCP 2026-07-28仕様と#3429のギャップ分析から始め、関連する#3658のpackaging issueも確認してください。このissueでは実装ではなく、ロードマップまたは明示的な決定を求めています。そのため、該当するmilestoneまたはlabelとともにDABのサポート方針が記録されれば完了です。
索引モデルが issue の本文から書いたものです。
説明
Summary
DAB's MCP server advertises and implements 2025-06-18 as a fixed default
(McpProtocolDefaults.DEFAULT_PROTOCOL_VERSION). Two spec revisions have shipped since:
2025-11-25 and 2026-07-28. #3429 analysed the gap to 2025-11-25 and was closed without
a follow-up item, and there is currently no issue tracking 2026-07-28 at all.
This issue asks for a decision and, if applicable, a roadmap entry — not necessarily an
immediate implementation.
Why this revision is different
2026-07-28 is not additive; it restructures the transport and lifecycle:
- Protocol-level sessions and the
Mcp-Session-Idheader are removed. - The
initialize/notifications/initializedhandshake is removed. Every request
carries its protocol version and client capabilities in_meta. - A new
server/discoverRPC is mandatory for advertising versions, capabilities and identity. - The GET stream endpoint and
resources/subscribeare replaced bysubscriptions/listen. - SSE resumability (
Last-Event-ID) is removed. MCP-Protocol-Version,Mcp-MethodandMcp-Nameheaders become required, with
server-side header/body validation (-32020 HeaderMismatch).- All results carry a
resultType; server-initiated requests are replaced by the
Multi Round-Trip Requests (MRTR) pattern. ping,logging/setLevelare removed; Roots, Sampling and Logging are deprecated.
Because the handshake itself is gone, the compatibility burden shifts entirely to clients.
The spec defines a probe-and-fall-back path, but a server that only speaks 2025-06-18
depends on every client retaining that path indefinitely. #3429 documented this failure mode
in practice (a client disconnecting on version downgrade over stdio).
What DAB would gain beyond conformance
Several of the changes map onto capabilities DAB users already ask for:
- Statelessness. With no protocol session, DAB instances become trivially scalable behind
a load balancer, and a restart no longer invalidates in-flight clients. It also removes the
Mcp-Session-Idfriction that the MCP Inspector guidance currently works around. ttlMs/cacheScopeontools/list,resources/list,resources/read. DAB already
has an entity cache with TTL; surfacing it at the protocol level would let clients stop
re-fetching. This matters at scale: our production configuration has 315 entities and
describe_entitiesresponses are substantial.- Deterministic tool ordering (a SHOULD in this revision) improves client-side caching and
LLM prompt-cache hit rates. Should be trivial, since DAB generates the tool surface. Mcp-Nameheader. Lets reverse proxies route, rate-limit and audit per tool without
parsing the request body. Today an operator behind nginx sees onlyPOST /mcpand cannot
tell which entity was read — a real gap for auditing.- Tasks extension (
io.modelcontextprotocol/tasks) is a natural fit for
aggregate_recordsover large tables.
Deployment context
Read-only ERP database exposed through DAB 2.0.9, HTTP transport behind an nginx reverse
proxy, 315 entities, consumed by MCP clients. Nothing is broken today — clients still
negotiate 2025-06-18 successfully over HTTP. The concern is that continued operation
depends on client-side backwards compatibility that operators do not control, while DAB has
no stated position.
Ask
- Is support for
2026-07-28on the roadmap? - If yes, could it be tracked with a milestone/label the way other MCP work is (
2.x,2.3)? - If no — please say so explicitly. A clear "DAB stays on
2025-06-18for now" is genuinely
actionable for operators, who can then plan a translating layer instead of waiting.
(Related: #3658, packagingMicrosoft.DataApiBuilder.Mcpas a NuGet SDK, would make such
a layer considerably cheaper to build.)
References
- Changelog for the revision: https://modelcontextprotocol.io/specification/2026-07-28/changelog
- Streamable HTTP transport: https://modelcontextprotocol.io/specification/2026-07-28/basic/transports/streamable-http
- #3429 — gap analysis for
2025-11-25(closed) - #3658 —
Microsoft.DataApiBuilder.McpNuGet package
- 主要言語
- C#
- スター
- 1.5k
- フォーク
- 372
- 平均マージ
- 7日 19時間
- マージ済み PR(30日)
- 10
コントリビューションガイド
はじめの一歩
- issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
- 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
- リポジトリをフォークし、ブランチを切って変更します。
- issue 番号を参照したプルリクエストを送ります。
Azure/data-api-builder のほかの issue
-
pgsql
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
Azure/data-api-builder#3598 ·
-
2.x cli mcp-server
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
Azure/data-api-builder#3576 ·
-
2.x health-endpoint
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
Azure/data-api-builder#3570 ·
-
2.x telemetry
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
Azure/data-api-builder#3564 ·
-
2.x telemetry
難易度 2/5 1〜3時間 初心者へのやさしさ 70/100
Azure/data-api-builder#3562 ·
Azure/data-api-builder の issue をすべて見る
似ている issue
-
untriaged
難易度 1/5 1時間未満 初心者へのやさしさ 88/100
dotnet/dotnet-api-docs#13095 ·
-
area-deployment area-integrations triage:bot-seen
難易度 2/5 半日 初心者へのやさしさ 86/100
-
type/automation type/tech-debt
難易度 2/5 1〜3時間 初心者へのやさしさ 84/100
-
bug
難易度 1/5 1時間未満 初心者へのやさしさ 90/100
newrelic/newrelic-dotnet-agent#3850 · コメント 1 件 ·
-
難易度 2/5 1〜3時間 初心者へのやさしさ 88/100
LuckyPennySoftware/AutoMapper#4660 ·