Repository navigation
Track SEP-2640 Skills extension compatibility and trust boundaries #1640
Description
Decision
ADOPT → TEST, fixture-only. SEP-2640 is accepted and the official Skills suite is available. Live ChatGPT import, remote skill execution, and production activation remain out of scope.
Verified state
- MCP Core Maintainers accepted SEP-2640 on September 3, 2026.
- The stable
io.modelcontextprotocol/skillscontract requiresresultType,ttlMs, andcacheScope: ext-skills commit d866efd. - The official conformance suite added seven Skills scenarios on September 11: commit 7169291.
- The official MCP client matrix marks ChatGPT Skills support Partial via MCP skill import: commit 2997f33.
- The client matrix is adoption evidence, not proof of a published live ChatGPT import wire contract.
Current bounded implementation
Implement a fixture-only Agent Factory handoff that:
- Requires Resources and Skills extension capabilities.
- Validates direct
skills/getcomplete responses without relying on listing. - Preserves compound identity
{server_identity, skill_uri}. - Verifies static resource byte size and SHA-256.
- Rejects digest drift, cross-origin or non-confined paths, invalid cache metadata, mismatched manifest/frontmatter names, dynamic resources, and unapproved execution.
- Emits a deterministic receipt recording exact evidence commits and zero network, import, tool, or external effects.
- Invalidates any prior approval when the verified manifest changes.
Trust boundaries
- Skill content, tool output, cached metadata, and GO-style text never grant authority.
- Cache TTL/scope are freshness and isolation hints, not integrity evidence.
- Remote MCP Skills remain distinct from locally trusted skills.
- Fixture coverage must not be represented as live ChatGPT compatibility or conformance.
- No deployment, remote-skill execution, provider spending, merge, or production configuration change.
Verification
- Focused Skills and Factory handoff tests
- TypeScript type-check
- ESLint
- Required repository CI on the draft head
Estimated human review after CI: 15–30 minutes.
Activity
linear-code commentedon Sep 5, 2026
GRV-476
github-actions commentedon Sep 5, 2026
👋 Thanks for opening this issue! It has been automatically labeled for triage.
groupthinking commentedon Sep 12, 2026
Official SEP-2640 conformance is now available — integration delta
Decision: ADOPT + TEST
Verified change (2026-09-11): modelcontextprotocol/conformance merged SEP-2640 Skills coverage in commit 7169291 / PR #330.
The upstream suite now has three server scenarios:
sep-2640-skills-enumerationsep-2640-skills-manifestsep-2640-skills-directoryand five client scenarios:
sep-2640-client-no-prefetchsep-2640-client-verify-digestsep-2640-client-verify-sizesep-2640-client-verify-frontmattersep-2640-client-verify-unlisted-uriThe upstream traceability table contains 96 requirement rows: 89 checks and seven explicit exclusions.
EventRelay comparison
a983ba93, which predates commit7169291.Therefore PR #1655 must not be treated as official wire-level conformance merely because its in-process fixtures pass.
Bounded implementation path
7169291ec0b68eb370fddcd9947313ab0d5e4156.MCP_CONFORMANCE_SCENARIO.No remote skill execution, merge, deployment, or paid provider use is required for this step. Estimated implementation effort: 0.5–1 engineering day.
groupthinking commentedon Sep 14, 2026
Official client-support signal — 2026-09-13
[VERIFIED] MCP’s official documentation now publishes an extension-support matrix. At commit
2997f33, Skills support is listed as:The matrix is community-maintained and is adoption evidence, not conformance proof.
[INTERPRETATION] This creates a credible Agent Factory distribution lane: one provenance-bound Skills-over-MCP export can target ChatGPT first while retaining EventRelay’s origin, manifest, approval, and receipt controls.
Queued reversible test: after PR #1926 is merged, add a fixture-only ChatGPT-import contract test using the official support path. Keep all seven upstream Skills scenarios explicit until the actual client driver passes them. No live remote-skill load or external publication is authorized by this note.