feat: make the skills verification catalog budget configurable per server (#2294)

Adds a Skills section to Server Settings with Maximum Number of Skills and
Maximum Catalog Size fields, defaulting to SKILL_MAX_CATALOG_SKILLS (256) and
SKILL_MAX_CATALOG_BYTES (64 MiB). The values persist as skillCatalogMaxSkills /
skillCatalogMaxBytes on the server's mcp.json entry (omitted at the default),
are validated as positive integers by the /api/servers routes, and are read by
verifySkills through getServerSettings(), so the CLI's --verify and the TUI
Skills pane both honor them.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P6i1HBSdSS9kL4npZ2dDSe
Signed-off-by: cliffhall <cliff@futurescale.com>
This commit is contained in:
cliffhall 2026-09-13 23:54:29 -04:00
commit eb41185c37

View file

@ -188,6 +188,8 @@ These have no analog in the broader `mcp.json` ecosystem. Each is **omitted on w
| `paginatedLists` | `false` | Fetch tools/resources/prompts one page at a time instead of auto-aggregating |
| `advertisedExtensions` | — | Per-extension overrides for what the Inspector declares in `capabilities.extensions` |
| `maxFetchRequests` | `1000` | Network-log retention for this server (`DEFAULT_MAX_FETCH_REQUESTS`); `0` means unlimited |
| `skillCatalogMaxSkills` | `256` | Most skills one skills verification run reads (`SKILL_MAX_CATALOG_SKILLS`) — the CLI's `--verify` and the TUI Skills pane. Positive integer; there is no unlimited value |
| `skillCatalogMaxBytes` | `67108864` | Most bytes one skills verification run reads (`SKILL_MAX_CATALOG_BYTES`, 64 MiB). Positive integer |
| `oauth` | — | `{ clientId, clientSecret, scopes, requestRefreshToken, revokeOnClear, authorizationParams, authorizationUrl, tokenUrl, enterpriseManaged, onInsufficientScope }` |
`metadata` is a JSON **object**, and its values may be any JSON — an object, an array, a number, a boolean, `null` — not only a string. The MCP spec does not restrict `_meta` value types in general, and the SDK models the field as a passthrough object, so the Inspector does not narrow it either ([#1910](https://github.com/modelcontextprotocol/inspector/issues/1910)). Edit it in Server Settings → Request Metadata, which is a JSON editor rather than the key/value rows `headers` and `env` use; text that is not a JSON object is flagged inline and not applied.