modelcontextprotocol/inspector
Watch
1
0
Fork
You've already forked inspector
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 2

feat: support the Skills extension (SEP-2640) with digest verification

Browse source 
Adds detection, enumeration, and conformance checking for the Skills
extension (`io.modelcontextprotocol/skills`) — phases 1 and 2 of #2234,
which is everything its Acceptance list names.

Skills is a *server*-declared extension, read off the connecting server's
`capabilities.extensions`, so it is deliberately absent from
`ADVERTISABLE_EXTENSIONS` — that registry is what the Inspector advertises
and the user toggles, and an entry there would be a meaningless toggle.

`skills/list` and `skills/get` are consumer-owned extension methods that
neither era codec defines, so the SDK's era gate skips them and they go out
as ordinary `client.request` calls with explicit result schemas. The
raw-wire channel modern `tasks/*` needs is not used, and the Skills tab is
not era-gated: a legacy-era server that declares the extension is serving it.

The checks are the point, not the list view. `core/mcp/skills.ts` reports
each obligation SEP-2640 states — the name/path invariant, the digest
format, the 512-entry and 16 MiB limits, and `resources: "dynamic"`, which
means integrity cannot be verified at all. Digest verification hashes the
fetched bytes with WebCrypto and returns a mismatch with both digests
attached rather than throwing, because showing a mismatch loudly is the
whole value proposition.

Files are fetched on demand: SEP-2640 is explicit that a `resources/read`
of a `SKILL.md` is not a load and confers no standing, so none of the SEP's
host machinery is implemented.

The `skills-http` fixture serves four skills over two pages, three of them
deliberately non-conforming — without those the verification code is
untestable.

Phase 3 (CLI, TUI, `resources/directory/read`, paged mode) is #2248.

Closes #2234

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018kfrH3uRNUM4JAk1reKtyY
Signed-off-by: cliffhall <cliff@futurescale.com>
This commit is contained in:
cliffhall 2026-09-04 20:01:13 -04:00
commit 63623b754b
1 changed files with 3684 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

6
clients/web/README.md
View file

@ -93,7 +93,7 @@ Nothing _enforces_ the boundary — no path alias keys off it, and the coverage
## Core tab automation contract
The Tools, Resources, and Prompts screens each expose a `data-testid` plus a
The Tools, Resources, Prompts and Skills screens each expose a `data-testid` plus a
small set of `data-*` attributes, so a headless driver can `waitForSelector` on
a deterministic signal rather than on visible copy. `scripts/smoke-web-tabs.mjs`
drives all three against `test-servers/configs/web-tabs-http.json` ([#2148](https://github.com/modelcontextprotocol/inspector/issues/2148)).
@ -114,6 +114,10 @@ Treat them as a public contract, for the same reason as the Apps ones below:
| `data-prompt-count` | on `prompts-screen`| Entries from `prompts/list`. |
| `data-get-status` | on `prompts-screen`| `idle` → `pending` → `ok` / `error` for the current `prompts/get`. |
| `data-testid="prompt-messages"` | messages panel | The fetched prompt's **rendered** messages — the `prompts/get` counterpart of `resource-preview`, and asserted alongside `data-get-status` for the same reason. |
| `data-testid="skills-screen"` | Skills root | The element carrying the two attributes below ([#2234](https://github.com/modelcontextprotocol/inspector/issues/2234)). Not driven by `smoke-web-tabs.mjs` yet — the attributes exist so it can be, and so a rename fails in the screen's unit test rather than later. |
| `data-skill-count` | on `skills-screen` | Entries accumulated from `skills/list`. |
| `data-skill-page-count` | on `skills-screen` | Pages the last `skills/list` walk took — a **separate** fact from the count, and the one that shows pagination actually happened. |
| `data-testid="skill-manifest"` | detail pane | The selected skill's resource manifest. Absent for a `resources: "dynamic"` skill, which has no manifest to render. |
Why attributes rather than text: a smoke that waited on a label fails the next
time the label is reworded, which is noise rather than signal — and it fails as