@kolbo/mcp 1.3.2 → 1.5.1

package/README.md

@@ -19,7 +19,7 @@ Add to `.claude/settings.json`:
   "mcpServers": {
     "kolbo": {
       "command": "npx",
-      "args": ["-y", "@kolbo/mcp"],
+      "args": ["-y", "@kolbo/mcp@latest"],
       "env": {
         "KOLBO_API_KEY": "kolbo_live_..."
       }
@@ -39,6 +39,8 @@ Just ask Claude naturally:
 - *"Make a lo-fi hip hop beat"*
 - *"Read this out loud with a British female voice"*
 - *"Ask Claude about the latest AI news with web search on"*
+- *"Analyze this video and tell me what prompts are shown on screen"*
+- *"What's in this image?"*
 - *"Create a Visual DNA profile called 'Alex' from these images"*
 
 ## Available Tools (30)
@@ -63,10 +65,10 @@ Just ask Claude naturally:
 
 Every image/video/creative-director tool accepts `visual_dna_ids` and `moodboard_id` for character/style consistency across outputs — you can compose `create_visual_dna` → `generate_image` (with the DNA applied server-side) in a single agent turn. `generate_creative_director` also accepts `moodboard_ids` plural for blending.
 
-**Chat**
+**Chat & Vision**
 | Tool | Description |
 |------|-------------|
-| `chat_send_message` | Multi-turn chat with any Kolbo model; supports web search and deep think |
+| `chat_send_message` | Multi-turn chat with any Kolbo model. Pass `media_urls` to analyze images, videos, or audio — auto-routes to Gemini for vision. Supports web search and deep think. |
 | `chat_list_conversations` | List past chat threads |
 | `chat_get_messages` | Fetch messages in a conversation |
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.3.2",
+  "version": "1.5.1",
   "description": "Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code",
   "main": "src/index.js",
   "bin": {

package/src/client.js

@@ -91,7 +91,7 @@ function xdgDataDir() {
 }
 
 /**
- * Read the Kolbo CLI's auth store. The CLI writes credentials to
+ * Read the Kolbo Code auth store. Kolbo Code writes credentials to
  * <xdg-data>/kolbo/auth.json after device-code login.
  *
  * On Windows (Git Bash / MSYS2) xdg-basedir resolves to ~/.local/share,

package/src/tools/chat.js

@@ -10,17 +10,18 @@ function registerChatTools(server, client) {
   // ─── chat_send_message ─────────────────────────────────────
   server.tool(
     'chat_send_message',
-    'Send a chat message to Kolbo AI. Starts a new conversation (omit session_id) or continues an existing one. Returns the assistant response when complete. Supports web search and deep think modes.',
+    'Send a chat message to Kolbo AI. Starts a new conversation (omit session_id) or continues an existing one. Returns the assistant response when complete. Supports image/video/audio analysis via media_urls — pass public URLs and the model auto-routes to a vision-capable model (e.g. Gemini) when media is detected. Supports web search and deep think modes.',
     {
       message: z.string().describe('The user message to send'),
-      model: z.string().optional().describe('Model identifier (e.g. "gpt-4o", "claude-sonnet-4-5"). Omit for Smart Select (auto).'),
+      model: z.string().optional().describe('Model identifier (e.g. "gpt-4o", "claude-sonnet-4-5", "gemini-2.5-pro"). Omit for Smart Select (auto). For image/video/audio analysis, prefer "gemini-2.5-pro" or omit to auto-route.'),
       session_id: z.string().optional().describe('Existing chat session ID to continue. Omit to start a new conversation.'),
       system_prompt: z.string().optional().describe('System prompt for the conversation. Only applied when creating a new session.'),
       web_search: z.boolean().optional().describe('Enable web search for this message. Default: false'),
       deep_think: z.boolean().optional().describe('Enable deep think (extended reasoning). Default: false'),
-      enhance_prompt: z.boolean().optional().describe('Enhance the prompt. Default: true')
+      enhance_prompt: z.boolean().optional().describe('Enhance the prompt. Default: true'),
+      media_urls: z.array(z.string()).optional().describe('Public URLs of images, videos, or audio files to analyze. The model auto-routes to a vision-capable model when media is present. Use upload_media first to get a public URL for local files.')
     },
-    async ({ message, model, session_id, system_prompt, web_search, deep_think, enhance_prompt }) => {
+    async ({ message, model, session_id, system_prompt, web_search, deep_think, enhance_prompt, media_urls }) => {
       const gen = await client.post('/v1/chat', {
         message,
         model,
@@ -28,7 +29,8 @@ function registerChatTools(server, client) {
         system_prompt,
         web_search,
         deep_think,
-        enhance_prompt
+        enhance_prompt,
+        media_urls
       });
 
       // Deep think reasoning can run far longer than normal chat. Also grant

package/src/tools/models.js

@@ -11,7 +11,7 @@ function registerModelTools(server, client) {
     'list_models',
     'List available AI models on Kolbo. Filter by type to find models for a specific generation type.',
     {
-      type: z.string().optional().describe('Filter by type: "image", "video", "video_from_image", "music", "speech", "sound". Omit for all models.')
+      type: z.string().optional().describe('Filter by type: "image", "image_edit", "video", "video_from_image", "video_from_video", "music", "speech", "sound", "chat", "lipsync", "three_d", "elements", "first_last_frame", "transcription". Omit for all models.')
     },
     async ({ type }) => {
       const path = type ? `/v1/models?type=${encodeURIComponent(type)}` : '/v1/models';

package/src/tools/moodboards.js

@@ -9,10 +9,15 @@ function registerMoodboardTools(server, client) {
   // ─── list_moodboards ───────────────────────────────────────
   server.tool(
     'list_moodboards',
-    'List moodboards available to you: your own, system presets, and any organization moodboards. Returns id, name, master_prompt, thumbnail, and image URLs for each.',
-    {},
-    async () => {
-      const result = await client.get('/v1/moodboards');
+    'List moodboards. By default returns ALL (personal + system presets + organization). Use "scope" to filter: "personal" (user\'s own), "preset" or "global" (system presets), or "organization" (org-shared). Returns id, name, master_prompt, thumbnail, and image URLs for each.',
+    {
+      scope: z.enum(['all', 'personal', 'preset', 'global', 'organization']).optional().describe('Filter by scope. Default: "all" (everything accessible). "personal" = only your own. "preset"/"global" = system presets. "organization" = org-shared.')
+    },
+    async ({ scope } = {}) => {
+      const params = new URLSearchParams();
+      if (scope && scope !== 'all') params.set('scope', scope);
+      const qs = params.toString();
+      const result = await client.get(`/v1/moodboards${qs ? '?' + qs : ''}`);
       return {
         content: [{
           type: 'text',

package/src/tools/visual_dna.js

@@ -76,10 +76,21 @@ function registerVisualDnaTools(server, client) {
   // ─── list_visual_dnas ──────────────────────────────────────
   server.tool(
     'list_visual_dnas',
-    'List your Visual DNA profiles. Returns id, name, type, and thumbnail for each.',
-    {},
-    async () => {
-      const result = await client.get('/v1/visual-dna');
+    'List Visual DNA profiles. By default returns ALL (personal + global cast presets + organization). Use "scope" to filter: "personal" (user\'s own), "global" (system cast/presets), or "organization" (org-shared). Use "search" to filter by name/tags/description. Use "collection" to filter global presets by collection (cast, influencers, props, locations, styles, glamour, street).',
+    {
+      scope: z.enum(['all', 'personal', 'global', 'organization']).optional().describe('Filter by scope. Default: "all" (everything accessible). "personal" = only your own. "global" = system presets/cast. "organization" = org-shared.'),
+      search: z.string().optional().describe('Search by name, tags, or description (case-insensitive)'),
+      collection: z.string().optional().describe('Filter global presets by collection: cast, influencers, props, locations, styles, glamour, street'),
+      tags: z.string().optional().describe('Comma-separated tags to filter by (OR logic)')
+    },
+    async ({ scope, search, collection, tags } = {}) => {
+      const params = new URLSearchParams();
+      if (scope && scope !== 'all') params.set('scope', scope);
+      if (search) params.set('search', search);
+      if (collection) params.set('collection', collection);
+      if (tags) params.set('tags', tags);
+      const qs = params.toString();
+      const result = await client.get(`/v1/visual-dna${qs ? '?' + qs : ''}`);
       return {
         content: [{
           type: 'text',