@vectros-ai/mcp-server 0.14.0 → 0.16.0

package/CHANGELOG.md

@@ -3,6 +3,46 @@
 All notable changes to `@vectros-ai/mcp-server` are documented here.
 This project adheres to [Semantic Versioning](https://semver.org).
 
+## 0.16.0 — 2026-08-27
+
+### Added
+
+- **`record_batch_get`** — fetch several structured records by id (1-100) in one call, each with its
+  full payload, wrapping `POST /v1/records/batch-get` (0.41.0: previously a `501` stub, now live).
+  Complements `record_get`: use this instead of N single-id calls when you already hold several ids
+  (e.g. hydrating a page of `record_query`/`hybrid_search` results). The API silently omits any id you
+  can't access with no per-id existence signal; the response also carries `missingIds` — every
+  requested id not present in `data` — so a caller can tell a partial result from a complete one
+  without diffing it by hand. Same per-record payload-truncation guard as `record_get`.
+- **Repinned to `@vectros-ai/sdk` 0.41.0** for the above. No other 0.41.0 surface change is consumed:
+  the issuer-update endpoint and the `roleIds` access-profile field are identity/access administration
+  this server's tools deliberately don't touch (`lookup_principal`'s own docstring: "identity CRUD
+  stays off the agent tool surface by design"); entity responses' new `contextId` field already flows
+  through `lookup_principal`'s pass-through JSON with no code change.
+
+## 0.15.0
+
+### Added
+
+- **`lookup_principal` accepts an optional `contextId`** for entity kinds (`org`/`client`/any
+  namespace you registered — not `user`, which is always tenant-wide). A namespace registration
+  can now be tenant-wide or owned by one app context (API 0.40.0). A context-confined credential's
+  own context resolves automatically without this; an unconfined (root-key) credential needs
+  `contextId` to reach a context-owned namespace's entities — omitting it previously read back an
+  empty result with no indication why. Two rejections come with it: supplying `contextId` with
+  `kind: "user"` now returns `isError: true` immediately (the user surface is always tenant-wide);
+  supplying it against a namespace that turns out to be tenant-wide is rejected by the API with a
+  `400`.
+
+### Changed
+
+- **Repinned to `@vectros-ai/sdk` 0.40.0.**
+- **`current_identity` (and the `identity` resource) now note that `granted_capabilities` — a scope
+  clause's API-0.40.0 reach dimension (`member-lifecycle` / `forensic-read` / `context-directory-read`
+  / `delegate-mint`) — isn't reported by `/v1/ping` yet**, so `allowedActions` + `dataScope` may
+  understate a credential's true reach. This is a description-accuracy fix (the tool no longer implies
+  it shows the complete picture); no new field ships, since the backend doesn't emit one yet.
+
 ## 0.14.0
 
 ### Changed

package/README.md

@@ -169,7 +169,7 @@ Add `-e VECTROS_API_BASE_URL=https://api.staging.vectros.ai` for a non-productio
 environment. Reopen the project in Claude Code and the Vectros tools are
 available.
 
-## Tools (21 tools)
+## Tools (22 tools)
 
 **Search & RAG**
 
@@ -186,6 +186,7 @@ available.
 | `list_schemas` | List the record-schema catalog the credential can see (filter by `surface` or resolve one by `recordType`). Makes `record_query` / `record_create` discoverable. |
 | `record_query` | Query records by lookup field — equality (`value`), range, or prefix, with `asc`/`desc` ordering and an optional `sortFrom`/`sortTo` window — or list mode (filter by ownership + type). Also supports composite equality across 2-3 fields (`values`), but only against a lookup the *schema* declares over those fields together (see `list_schemas`) — not any two fields you pick. |
 | `record_get` | Fetch one record by id, including its full payload (large payloads truncated to protect the agent context window). |
+| `record_batch_get` | Fetch several records by id (1-100) in one call, each with its full payload. Returns `missingIds` for any requested id you can't access, since the API silently omits them. |
 | `record_create` | Create a record of a given type; idempotent by `externalId`; optional per-record `indexMode`. |
 | `record_update` | Patch a record's payload (deep-merged; `null` deletes a key); optimistic concurrency via `expectedVersion`. |
 | `record_delete` | Permanently delete a record by id (leaves a tombstone). |
@@ -213,11 +214,11 @@ available.
 
 | Tool | What it does |
 |---|---|
-| `current_identity` | Describe the credential: tenantId, environment, principalType, principalKeyId, and (for scoped credentials) allowedActions + dataScope. Also reports this server's own version and the bundled SDK version (`mcpServerVersion`, `sdkVersion`). |
-| `lookup_principal` | Resolve a user / org / client by your own `externalId` (→ its Vectros UUID, for the ownership filters) or by a schema lookup field. Read-only. |
+| `current_identity` | Describe the credential: tenantId, environment, principalType, principalKeyId, principalLabel, and (for scoped credentials) allowedActions + dataScope. Does **not** yet include `granted_capabilities` (`member-lifecycle` / `forensic-read` / `context-directory-read` / `delegate-mint`) — a separate reach dimension a scope clause can carry as of API 0.40.0 that `/v1/ping` doesn't report yet, so allowedActions + dataScope may understate a credential's true reach. Also reports this server's own version and the bundled SDK version (`mcpServerVersion`, `sdkVersion`). |
+| `lookup_principal` | Resolve a user, or an identity entity in a namespace (`org`/`client`/any namespace you registered), by your own `externalId` (→ its Vectros UUID, for the ownership filters) or by a schema lookup field. Pass `contextId` to target a specific app context for a context-owned namespace. Read-only. |
 | `version_history` | Read the audit/version trail (CREATE/UPDATE/DELETE, with actor + diff) for one record or document. Read-only. |
 
-All 21 tools wrap published Vectros HTTP API endpoints. JSON
+All 22 tools wrap published Vectros HTTP API endpoints. JSON
 responses are what the agent sees as tool output. Per-call cost
 surfaces via the `usage` field on inference responses.