@labelgrid/mcp 0.6.1 → 0.8.0

package/CHANGELOG.md

@@ -5,6 +5,54 @@ All notable changes to `@labelgrid/mcp` are documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+## [0.8.0] - 2026-09-30
+
+### Security
+
+- Refresh the desktop bundle's locked production dependencies to patched
+  compatible versions. The MCP SDK remains on v1.
+
+### Fixed
+
+- Oversized tool responses now return a bounded `RESULT_TOO_LARGE` error instead
+  of a serialized data prefix that could exceed the 400,000-character limit.
+  Write operations may already have completed; check their state before retrying.
+- Oversized API and handler errors remain valid JSON, preserving bounded
+  diagnostic fields and explicitly marking omitted details.
+- An oversized error keeps its `blocking_issues` list when the error fits after
+  bulky API details are dropped; otherwise the list may be truncated.
+
+### Changed
+
+- `get_delivery_queue` now requires `release_id` and returns the public API's
+  canonical release delivery status, including aggregate state, historical
+  predicates, and one current state per outlet. It no longer reads or interprets
+  raw distribution queue rows; the former outlet, status, and pagination inputs
+  have been removed.
+- `confirm_review` documents the `blocking_issues_open` error: it lists the
+  blocking issues to resolve, or to answer with a review-issue note, before
+  retrying.
+- `enable_beatport` no longer describes onboarding as one-time. Declined or
+  canceled requests can be submitted again; a pending request or an already
+  verified label does not start another one.
+
+## [0.7.0] - 2026-08-20
+
+### Added
+
+- `delete_catalog_item` accepts `replace_with` for writers and publishers. The
+  replacement receives every credit before the original is deleted. Other
+  entity types reject the parameter without sending a delete request.
+- `query_financials` concise responses include `credit_amount`, preserving
+  positive, zero and explicit null values from the API.
+
+### Changed
+
+- Writer and publisher deletion guidance now names all references that can
+  block deletion and documents the `REPLACEMENT_UNAVAILABLE` response.
+
 ## [0.6.1] - 2026-08-05
 
 ### Changed

package/README.md

@@ -129,7 +129,7 @@ tool definitions by `npm run gen-docs` — do not edit it by hand._
 | `get_catalog_item` | read | Retrieve one catalog entity by id, with full detail (e.g. a release’s metadata and track listing, a track’s contributors and royalty splits, a writer’s PRO/IPI). |
 | `create_catalog_item` | write | Create a catalog entity: pass its attributes in `fields` — the API owns all validation. Required and common fields per entity: label — required: name, default_email; optional: support email, website/platform URLs, default copyright lines, isrc_base. artist — required: artist_name; optional: full_name, email, location, bios, isni, default_language, platform profile URLs. writer — required: first_name, last_name; optional: middle_name, display_credits, email, country, pro, ipi, isni, publisher_id (or publisher_name/publisher_pro/publisher_ipi). publisher — required: name; optional: ipi, pro, isni, controlled_publisher. release — required on create: content_type, label_id, artists, titles, cat (catalog number), artwork_ai_usage, primary_genre_id; many optional fields (dates, copyright lines, genres, per-outlet URLs). track — required on create: release_id, disc, track_num, composition_type, artists, audio_ai_usage, composition_ai_usage, commercial_samples, audio_language, contributors, and recording_country (ISO 3166-1 alpha-2, e.g. "US"); optional: titles, isrc, iswc, writers, publishers, splits, and more. A release is created in DRAFT state — add tracks, then run the release checks before distributing. |
 | `update_catalog_item` | write | Update a catalog entity: supply only the fields to change in `fields` (same field sets as create_catalog_item). Once a release is submitted or distributed, some release and track fields are locked — changing one returns a 403 with code RELEASE_LOCKED_FIELDS naming exactly which fields cannot change. |
-| `delete_catalog_item` | write | Delete a catalog entity. The API refuses deletes that would orphan data — label: refused while the label still has releases — remove or reassign its releases first. artist: refused while still referenced by releases or tracks. writer: refused while still referenced by tracks. publisher: refused while still referenced by writers. release: only a never-submitted draft can be deleted. track: refused once the release is no longer an editable draft. |
+| `delete_catalog_item` | write | Delete a catalog entity. The API refuses deletes that would orphan data — label: refused while the label still has releases — remove or reassign its releases first. artist: refused while still referenced by releases or tracks. writer: refused while still referenced by tracks or artists, unless replace_with reassigns those credits. publisher: refused while still referenced by tracks or label default publishers, unless replace_with reassigns those credits. release: only a never-submitted draft can be deleted. track: refused once the release is no longer an editable draft. `replace_with` — writer and publisher only — is the id inheriting those credits; a 422 REPLACEMENT_UNAVAILABLE means nothing was deleted. |
 | `upload_image` | write | Upload a label image (logo, dark-mode logo, or background) or an artist photo from a local image file, per `target`. |
 | `get_asset` | read | Read a track or release asset. Valid combinations: (1) mode='info' + parent='track' + asset stereo\|dolby\|lyrics — file metadata (not the bytes) incl. processing state. (2) mode='info' + parent='release' + asset square\|tall — motion-artwork (animated cover) video metadata. (3) mode='download_url' + parent='track' + asset audio_16\|audio_24\|audio_32 (WAV master) or audio_preview_full\|audio_preview_clip (MP3 preview) — returns { download_url, expires_in }, a signed URL that expires roughly 10 minutes after issue; fetch it directly — do not send your API token to it. Any other combination is refused. |
 
@@ -138,7 +138,7 @@ tool definitions by `npm run gen-docs` — do not edit it by hand._
 | Tool | Gate | Description |
 | --- | --- | --- |
 | `get_release_review` | read | Read a release's automated quality-check results. Pick ONE view with `view`: `issues` lists the review issues raised against the release — each with a code (see list_reference_data type issue_definitions), severity, and whether it blocks distribution. `quality_report` returns the Preflight QC quality report — customer-facing issues to review before confirming distribution; Preflight QC is an optional add-on — without it the API returns a 403, surfaced verbatim. |
-| `get_delivery_queue` | read | List your account's distribution queue, paginated — one entry per (release, outlet) delivery with its status (e.g. pending review, processing, scheduled, complete, error). Filter by `release_id`, `outlet_id`, or `status`. |
+| `get_delivery_queue` | read | Read a release's canonical delivery status: its overall state, current and historical delivery predicates, and one current state per outlet. The API owns all queue-history interpretation. A release outside your account is indistinguishable from an unknown release (`RELEASE_NOT_ACCESSIBLE`). |
 | `get_landing_config` | read | Retrieve a release's smart-link landing-page configuration: enabled state, style/mode, custom copy, action list, pre-order links. Change it via manage_release_links (action update_landing_config). |
 | `list_track_licenses` | read | List a track's licenses (e.g. cover/mechanical or sample clearances), paginated. Pass `license_id` to retrieve one license instead. |
 | `run_release_checks` | write | Run an automated check on a release. Pick ONE with `check`: `validate` returns problems that would block distribution (human-readable `errors` + machine-readable `errors_structured`); it changes nothing and is safe to repeat — run it before distributing. `refresh_quality_report` re-runs the Preflight QC checks (read the report with get_release_review view quality_report); an hourly refresh budget may rate-limit frequent calls. Preflight QC is an optional add-on. |
@@ -177,8 +177,8 @@ tool definitions by `npm run gen-docs` — do not edit it by hand._
 | `manage_track_license` | full-write | Manage license documents on a track (cover or cleared sample). `upload` attaches a new license — `file_path` required, `type` selects cover/sample; optional metadata fields. `update` replaces the file and/or metadata — `track_license_id` (from list_track_licenses) and `file_path` required. `delete` permanently removes a license and its file — `track_license_id` required; cannot be undone. Immutability-governed once the release is live. |
 | `distribute_release` | full-write | Submit a release to the stores/outlets — the FINAL action that sends it out; run_release_checks (check validate) should pass first. The server enforces the account’s weekly submission limit. Reuse the SAME idempotency_key when retrying an unobserved call; without one each call is a new submission. |
 | `takedown_release` | full-write | Take a release down from ALL outlets/stores — a final action that removes it everywhere it was delivered. Re-distribution is a fresh submission. |
-| `confirm_review` | full-write | Confirm a release Preflight QC placed on hold, moving it into distribution review, after reviewing the quality report and accepting the release as-is. Safe to repeat. |
-| `enable_beatport` | full-write | Request Beatport onboarding for a label. One-time and cannot be un-requested — confirm the label is correct first. |
+| `confirm_review` | full-write | Confirm a release Preflight QC placed on hold, moving it into distribution review, after reviewing the quality report and accepting the release as-is. If blocking issues remain, the blocking_issues_open error includes blocking_issues to resolve or answer with a review-issue note before retrying. Safe to repeat. |
+| `enable_beatport` | full-write | Request Beatport onboarding for a label. Declined or canceled requests can be submitted again; pending requests and verified labels do not start another request. Confirm the label is correct first. |
 
 <!-- TOOLS:END -->
 
@@ -238,7 +238,7 @@ Version 0.3.0 is a **breaking release**: the 83 per-endpoint tools were consolid
 | `list_artificial_streams` | `query_artificial_streaming` (`view: 'records'`) |
 | `get_artificial_fee_breakdown` | `query_artificial_streaming` (`view: 'fee_breakdown'`, `period: 'YYYY-MM'`) |
 | `get_analytics` | `get_analytics` (unchanged) |
-| `get_delivery_queue` | `get_delivery_queue` (unchanged) |
+| `get_delivery_queue` | `get_delivery_queue` (`release_id` is now required; returns canonical delivery status) |
 | `get_landing_config` | `get_landing_config` (unchanged) |
 | `list_statements` | `query_financials` (`view: 'statements'`) |
 | `get_statement` | `query_financials` (`view: 'statement_detail'`, `invoice_number: …`) |
@@ -292,7 +292,7 @@ The server has three gates. Each is fail-closed: a tool is only registered — a
    - **distribute a release to stores** — a final submission subject to your account's weekly limit,
    - **take a release down from all stores**,
    - confirm a held release into review,
-   - request one-time Beatport onboarding for a label.
+   - request Beatport onboarding for a label; declined or canceled requests can be submitted again.
 
 Leaving `LABELGRID_ENABLE_FULL_WRITES` unset is the safe default: your AI assistant can prepare and validate everything, but the irreversible submission stays a deliberate, opt-in step.
 

package/dist/coverage.js

@@ -58,7 +58,7 @@ export const COVERAGE = {
     'GET /stream-radar/flags': 'query_artificial_streaming',
     'GET /stream-radar/flags/{streamRadarFlag}': 'query_artificial_streaming',
     // delivery
-    'GET /queues/distro': 'get_delivery_queue',
+    'GET /releases/{releaseId}/delivery-status': 'get_delivery_queue',
     'GET /releases/{release}/landing-config': 'get_landing_config',
     // finance
     'GET /statements': 'query_financials',
@@ -141,15 +141,18 @@ export const EXCLUDED = {
     'GET /analytics/streams-by-age': 'served by get_analytics (summary)',
     'GET /analytics/shares-by-country': 'served by get_analytics (summary)',
     // Alternate/adjacent surfaces intentionally not exposed in v1.
+    'GET /queues/distro': 'raw queue history — use the canonical release delivery status projection instead',
     'POST /releases/{release}/withdraw-review': 'withdraw-review flow — not exposed in v1',
     'GET /resolve/label/{labelSlug}': 'label-website resolution — not exposed in v1',
     'GET /site-settings/{label}': 'label-website settings — not exposed in v1',
     'GET /site-settings/links/{label}': 'label-website settings — not exposed in v1',
+    'GET /tracks/{track}/file-upload-attempts/{uploadAttempt}': 'per-upload audio processing status — not exposed in v1',
     'GET /tracks/{track}/licenses/{trackLicense}/download': 'license file download — not exposed in v1',
     'GET /transactions/csv': 'transaction CSV export — not exposed in v1',
 };
 export const PENDING_DOCS = {
     'GET /account': 'get_account',
     'GET /analytics/availability': 'get_analytics_availability',
+    'GET /releases/{releaseId}/delivery-status': 'get_delivery_queue',
     'GET /tracks/{track}/files/{assetType}/download-url': 'get_asset',
 };

package/dist/projection.js

@@ -55,7 +55,17 @@ export const CONCISE_ALLOWLISTS = {
         'message',
         'created_at',
     ],
-    get_delivery_queue: ['status', 'outlet', 'outlet_id', 'delivered_at', 'created_at', 'type'],
+    get_delivery_queue: [
+        'state',
+        'currently_live',
+        'ever_submitted',
+        'ever_delivered',
+        'outlet',
+        'operation',
+        'queue_id',
+        'updated_at',
+        'error_code',
+    ],
     query_artificial_streaming: [
         'dsp',
         'country',
@@ -72,6 +82,7 @@ export const CONCISE_ALLOWLISTS = {
         'status',
         'currency',
         'gross_usd',
+        'credit_amount',
         'labelgrid_fee',
         'platform_fee_usd',
         'ugc_fee_usd',

package/dist/tools/catalog.js

@@ -11,7 +11,7 @@
  * `response_format: 'detailed'` returning the verbatim API response.
  */
 import { statSync } from 'node:fs';
-import { ENTITIES, ENTITY_NAMES, assertAllowedExtension, } from '@labelgrid/core';
+import { ENTITIES, ENTITY_NAMES, REPLACEMENT_ENTITIES, assertAllowedExtension, } from '@labelgrid/core';
 import { z } from 'zod';
 import { applyProjection } from '../projection.js';
 /** Accepted image extensions for the catalog image uploads. */
@@ -135,17 +135,47 @@ const updateCatalogItem = {
         return client.patch(`${spec.path}/${args.id}`, args.fields);
     },
 };
+/** 'writer and publisher' — read off the registry, never spelled out by hand. */
+const REPLACEMENT_ENTITY_LIST = REPLACEMENT_ENTITIES.join(' and ');
 const deleteCatalogItem = {
     name: 'delete_catalog_item',
     toolset: 'catalog',
     gate: 'safe_write',
     title: 'Delete a catalog item',
-    description: `Delete a catalog entity. The API refuses deletes that would orphan data — ${entityDoc((s) => s.deleteNote)}`,
-    inputShape: { entity: entityArg, id: idArg },
+    description: `Delete a catalog entity. The API refuses deletes that would orphan data — ${entityDoc((s) => s.deleteNote)}` +
+        ` \`replace_with\` — ${REPLACEMENT_ENTITY_LIST} only — is the id inheriting those credits; a 422 REPLACEMENT_UNAVAILABLE means nothing was deleted.`,
+    inputShape: {
+        entity: entityArg,
+        id: idArg,
+        replace_with: z
+            .number()
+            .int()
+            .positive()
+            .optional()
+            .describe(`${REPLACEMENT_ENTITY_LIST} only: the id that takes over every credit held by the one being deleted.`),
+    },
     annotations: { destructiveHint: true },
     handler: (args, { client }) => {
-        const spec = ENTITIES[args.entity];
-        return client.delete(`${spec.path}/${args.id}`);
+        const entity = args.entity;
+        const spec = ENTITIES[entity];
+        const path = `${spec.path}/${args.id}`;
+        const replaceWith = args.replace_with;
+        if (replaceWith === undefined) {
+            return client.delete(path);
+        }
+        // Only two endpoints take the parameter. Dropping it for the others would
+        // delete on the caller's behalf while silently ignoring the reassignment
+        // they asked for, so the call is refused before anything is sent.
+        if (!spec.acceptsDeleteReplacement) {
+            return Promise.resolve({
+                error: {
+                    code: 'INVALID_SELECTOR',
+                    message: `The ${entity} delete does not accept replace_with — only ${REPLACEMENT_ENTITY_LIST} deletes do. Delete without it, or clear the references first.`,
+                    status: 0,
+                },
+            });
+        }
+        return client.delete(path, { replace_with: replaceWith });
     },
 };
 /** Maps the label image targets to the API's imageType path segment. */

package/dist/tools/distribution.d.ts

@@ -7,7 +7,7 @@
  * These wrap: finalized audio/artwork/motion-artwork uploads (via the
  * presigned-URL flow or multipart), license file management, the FINAL
  * distribute/takedown actions, the Preflight-QC confirm-review step, and
- * one-time Beatport onboarding.
+ * Beatport onboarding.
  */
 import type { ToolDef } from './types.js';
 export declare const distributionTools: ToolDef[];

package/dist/tools/distribution.js

@@ -7,7 +7,7 @@
  * These wrap: finalized audio/artwork/motion-artwork uploads (via the
  * presigned-URL flow or multipart), license file management, the FINAL
  * distribute/takedown actions, the Preflight-QC confirm-review step, and
- * one-time Beatport onboarding.
+ * Beatport onboarding.
  */
 import { assertAllowedExtension, uploadViaPresignedUrl } from '@labelgrid/core';
 import { z } from 'zod';
@@ -239,7 +239,7 @@ const confirmReview = {
     toolset: 'distribution',
     gate: 'full_write',
     title: 'Confirm a held release into review',
-    description: 'Confirm a release Preflight QC placed on hold, moving it into distribution review, after reviewing the quality report and accepting the release as-is. Safe to repeat.',
+    description: 'Confirm a release Preflight QC placed on hold, moving it into distribution review, after reviewing the quality report and accepting the release as-is. If blocking issues remain, the blocking_issues_open error includes blocking_issues to resolve or answer with a review-issue note before retrying. Safe to repeat.',
     inputShape: { release_id: releaseId },
     annotations: { destructiveHint: true, idempotentHint: true },
     handler: (args, { client }) => client.post(`/releases/${args.release_id}/confirm-review`),
@@ -249,7 +249,7 @@ const enableBeatport = {
     toolset: 'distribution',
     gate: 'full_write',
     title: 'Request Beatport onboarding for a label',
-    description: 'Request Beatport onboarding for a label. One-time and cannot be un-requested — confirm the label is correct first.',
+    description: 'Request Beatport onboarding for a label. Declined or canceled requests can be submitted again; pending requests and verified labels do not start another request. Confirm the label is correct first.',
     inputShape: { label_id: z.number().int().positive().describe('The label id.') },
     annotations: { destructiveHint: true },
     handler: (args, { client }) => client.post(`/labels/${args.label_id}/enable-beatport`),

package/dist/tools/releases.d.ts

@@ -1,5 +1,5 @@
 /**
- * Releases toolset: release-level reads (review results, the delivery queue,
+ * Releases toolset: release-level reads (review results, delivery status,
  * the smart-link landing config, track licenses) plus the safe-write release
  * checks, landing-page management and review-issue notes.
  *

package/dist/tools/releases.js

@@ -1,5 +1,5 @@
 /**
- * Releases toolset: release-level reads (review results, the delivery queue,
+ * Releases toolset: release-level reads (review results, delivery status,
  * the smart-link landing config, track licenses) plus the safe-write release
  * checks, landing-page management and review-issue notes.
  *
@@ -39,27 +39,15 @@ const getDeliveryQueue = {
     name: 'get_delivery_queue',
     toolset: 'releases',
     gate: 'read',
-    title: 'Get the distribution queue',
-    description: "List your account's distribution queue, paginated — one entry per (release, outlet) delivery with its status (e.g. pending review, processing, scheduled, complete, error). Filter by `release_id`, `outlet_id`, or `status`.",
+    title: 'Get release delivery status',
+    description: "Read a release's canonical delivery status: its overall state, current and historical delivery predicates, and one current state per outlet. The API owns all queue-history interpretation. A release outside your account is indistinguishable from an unknown release (`RELEASE_NOT_ACCESSIBLE`).",
     inputShape: {
-        release_id: z.number().int().positive().optional().describe('Filter to one release.'),
-        outlet_id: z.number().int().positive().optional().describe('Filter to one outlet/store.'),
-        status: z.string().optional().describe('Filter by delivery status.'),
-        page: z.number().int().positive().optional(),
-        per_page: z.number().int().positive().optional(),
+        release_id: releaseId,
         response_format: responseFormat,
     },
     annotations: { readOnlyHint: true },
     handler: async (args, { client }) => {
-        const result = await client.get('/queues/distro', {
-            page: args.page,
-            per_page: args.per_page,
-            filter: {
-                release_id: args.release_id,
-                outlet_id: args.outlet_id,
-                status: args.status,
-            },
-        });
+        const result = await client.get(`/releases/${args.release_id}/delivery-status`);
         return applyProjection(result, 'get_delivery_queue', args.response_format);
     },
 };

package/dist/tools/types.js

@@ -14,14 +14,22 @@ export function toToolResult(r) {
     if ('data' in r) {
         const text = JSON.stringify(r.data ?? null, null, 2);
         if (text.length > MAX_TOOL_TEXT) {
-            // Reserve headroom for the wrapper keys so the whole envelope, not just the
-            // prefix, stays under the ceiling.
-            const wrapped = JSON.stringify({
-                truncated: true,
-                note: 'Response truncated — use pagination or filters to narrow the request.',
-                data_prefix: text.slice(0, MAX_TOOL_TEXT - 1_000),
-            }, null, 2);
-            return { content: [{ type: 'text', text: wrapped }] };
+            return {
+                content: [
+                    {
+                        type: 'text',
+                        text: JSON.stringify({
+                            error: {
+                                code: 'RESULT_TOO_LARGE',
+                                message: 'Response exceeded the 400,000-character limit; response data was omitted.',
+                                status: 0,
+                                suggestion: 'Use pagination or filters to narrow reads. If this was a write, it may already have completed. Check its state before retrying.',
+                            },
+                        }, null, 2),
+                    },
+                ],
+                isError: true,
+            };
         }
         return { content: [{ type: 'text', text }] };
     }
@@ -29,24 +37,46 @@ export function toToolResult(r) {
     if (errorText.length <= MAX_TOOL_TEXT) {
         return { content: [{ type: 'text', text: errorText }], isError: true };
     }
-    // The only unbounded fields are the verbatim API passthroughs; drop them so the
-    // envelope stays under the ceiling while the diagnostic core (code/message/
-    // status/suggestion) survives intact.
+    // Omit bulky API details first, preserving the diagnostic core when it fits.
+    // Blocking issues are what a caller needs to recover, so they are kept
+    // unless they are too large on their own.
     const bounded = { ...r.error };
     if (bounded.errors !== undefined)
         bounded.errors = '[truncated]';
     if (bounded.errors_structured !== undefined)
         bounded.errors_structured = '[truncated]';
+    if (bounded.details !== undefined)
+        bounded.details = '[truncated]';
     const boundedText = JSON.stringify({ error: bounded }, null, 2);
     if (boundedText.length <= MAX_TOOL_TEXT) {
         return { content: [{ type: 'text', text: boundedText }], isError: true };
     }
-    // Even after dropping the passthroughs the envelope is over the ceiling — a
-    // hostile error whose own code/message is huge. Hard-slice the serialized text
-    // at MAX_TOOL_TEXT and return it as-is: the result is no longer valid JSON, but
-    // an over-limit hostile error forfeits pretty structure to keep the hard bound.
+    if (bounded.blocking_issues !== undefined) {
+        bounded.blocking_issues = '[truncated]';
+        const withoutIssuesText = JSON.stringify({ error: bounded }, null, 2);
+        if (withoutIssuesText.length <= MAX_TOOL_TEXT) {
+            return { content: [{ type: 'text', text: withoutIssuesText }], isError: true };
+        }
+    }
+    // Bound raw fields before encoding. Four string prefixes of at most 8,000 code units
+    // leave room even when JSON escaping expands each code unit to six characters.
+    const compact = {
+        code: boundDiagnostic(bounded.code),
+        message: boundDiagnostic(bounded.message),
+        status: bounded.status,
+        field: bounded.field === undefined ? undefined : boundDiagnostic(bounded.field),
+        suggestion: bounded.suggestion === undefined ? undefined : boundDiagnostic(bounded.suggestion),
+        retry_after_seconds: bounded.retry_after_seconds,
+        errors: bounded.errors,
+        errors_structured: bounded.errors_structured,
+        details: bounded.details,
+        blocking_issues: bounded.blocking_issues,
+    };
     return {
-        content: [{ type: 'text', text: boundedText.slice(0, MAX_TOOL_TEXT) }],
+        content: [{ type: 'text', text: JSON.stringify({ error: compact }, null, 2) }],
         isError: true,
     };
 }
+function boundDiagnostic(value) {
+    return value.length > 8_000 ? `${value.slice(0, 8_000)} [truncated]` : value;
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@labelgrid/mcp",
-  "version": "0.6.1",
+  "version": "0.8.0",
   "mcpName": "io.github.labelgrid/labelgrid-mcp",
   "description": "Official LabelGrid MCP server — connect your AI client to your LabelGrid account",
   "type": "module",
@@ -27,7 +27,7 @@
     "node": ">=20"
   },
   "dependencies": {
-    "@labelgrid/core": "0.2.1",
+    "@labelgrid/core": "0.2.3",
     "@modelcontextprotocol/sdk": "^1.12.0",
     "zod": "^3.24.0"
   }

package/server.json

@@ -2,7 +2,7 @@
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
   "name": "io.github.labelgrid/labelgrid-mcp",
   "description": "Official LabelGrid MCP server — manage your music catalog, releases, analytics and distribution.",
-  "version": "0.6.1",
+  "version": "0.8.0",
   "websiteUrl": "https://labelgrid.com",
   "repository": {
     "url": "https://github.com/labelgrid/labelgrid-mcp",
@@ -12,7 +12,7 @@
     {
       "registryType": "npm",
       "identifier": "@labelgrid/mcp",
-      "version": "0.6.1",
+      "version": "0.8.0",
       "transport": {
         "type": "stdio"
       },