wolfpack-mcp 1.0.27 → 1.0.29

package/README.md

@@ -77,24 +77,24 @@ After saving the configuration, restart Claude Desktop to connect.
 | **Journal**    | "Log my standup notes" / "What did I work on last week?"                              |
 | **Radar**      | "What initiatives are in progress?" / "Show the roadmap"                              |
 
-## Multi-Team Users
+## Multiple Projects
 
-If you belong to multiple teams, Claude will ask which team you mean, or you can specify:
+If you belong to multiple project teams, Claude will ask which team you mean, or you can specify:
 
 - "Show my work items for the Platform team"
 - Use `list_teams` to see all your teams
 
-To pre-select a default team, add to your config:
+To pre-select a default team, add `WOLFPACK_TEAM_SLUG` to your config:
 
 ```json
-"env": {
-"WOLFPACK_API_KEY": "wfp_sk_your_api_key_here",
-"WOLFPACK_TEAM_SLUG": "your-team-slug"
+{
+  "env": {
+    "WOLFPACK_API_KEY": "wfp_sk_your_api_key_here",
+    "WOLFPACK_TEAM_SLUG": "your-team-slug"
+  }
 }
 ```
 
-## Project Focus
-
 The MCP server is designed to work within **one project at a time**:
 
 - The agent will identify which project you're working in before taking actions
@@ -102,53 +102,6 @@ The MCP server is designed to work within **one project at a time**:
 - The agent will not perform bulk actions across multiple projects
 - To switch projects, explicitly tell Claude (e.g., "switch to the Platform project")
 
-## API Key Permissions
-
-When creating your API key, select the permissions you need:
-
-| Permission              | What It Enables                 |
-| ----------------------- | ------------------------------- |
-| `mcp:work_items:read`   | View your tasks                 |
-| `mcp:work_items:create` | Create new tasks                |
-| `mcp:work_items:update` | Update task status and notes    |
-| `mcp:issues:read`       | View issues                     |
-| `mcp:issues:create`     | File new issues                 |
-| `mcp:issues:update`     | Update issue status and details |
-| `mcp:wiki:read`         | Read documentation              |
-| `mcp:wiki:create`       | Create new pages                |
-| `mcp:wiki:update`       | Edit existing pages             |
-| `mcp:journal:read`      | View journal entries            |
-| `mcp:journal:create`    | Create journal entries          |
-| `mcp:journal:update`    | Edit journal entries            |
-| `mcp:comments:create`   | Add comments to items           |
-| `mcp:radar:read`        | View initiatives and roadmap    |
-
-## Troubleshooting
-
-**"WOLFPACK_API_KEY environment variable is required"**
-Check that your Claude Desktop config has the API key set correctly.
-
-**"Invalid API key format"**
-API keys must start with `wfp_sk_` (user keys) or `wfp_ak_` (org-managed agent keys).
-
-**"Invalid API key"**
-Your key may be incorrect or revoked. Generate a new one from Account Settings.
-
-**"API key does not have permission: mcp:..."**
-Create a new key with the required permission enabled.
-
-**Connection errors**
-Verify [wolfpacks.work](https://wolfpacks.work) is accessible from your network.
-
-## Security
-
-- API keys are scoped to your account and team memberships
-- Permissions are configurable per key—grant only what you need
-- Revoke keys anytime from Account Settings
-
-For additional security, you can **restrict API keys to specific projects** when creating them in Account Settings. This
-ensures the key can only access the projects you select, regardless of your team memberships.
-
 ## Available Tools Reference
 
 <details>
@@ -167,10 +120,18 @@ List all teams you have access to.
 
 #### `list_work_items`
 
-Lists work items assigned to you (excludes completed by default).
+Lists work items on the Kanban board or backlog (excludes completed/closed by default).
 
 - `team_id` (optional): Filter by team
-- `status` (optional): Filter by status (new, doing, review, completed, blocked)
+- `status` (optional): Filter by status (new, doing, review, ready, blocked, completed, pending/backlog, all)
+- `assigned_to_id` (optional): Filter by assignee ("all", "me", "unassigned", or a user ID)
+- `search` (optional): Text search in title and description
+- `category_id` (optional): Filter by category ID, or "none" for uncategorized
+- `priority` (optional): Filter by priority level (0-4)
+- `radar_item_id` (optional): Filter by linked radar/initiative item
+- `date_from`, `date_to` (optional): Filter by creation date (ISO format, e.g. "2025-01-01")
+- `sort_by` (optional): Sort field (dateUpdated, dateCreated, priority, title)
+- `sort_order` (optional): Sort direction (desc, asc)
 - `limit`, `offset` (optional): Pagination
 
 #### `get_work_item`
@@ -201,6 +162,20 @@ Change work item status.
 - `work_item_id` (required): The work item ID
 - `status` (required): New status
 
+#### `update_work_item_assignee`
+
+Change the assignee on a work item.
+
+- `work_item_id` (required): The work item ID
+- `leading_user_id` (required): User ID to assign, or null to unassign
+
+#### `pull_work_item`
+
+Pull a work item from the backlog to the board (sets status to "new" and assigns to you).
+
+- `work_item_id` (required): The work item ID
+- `leading_user_id` (optional): User ID to assign (defaults to API key owner)
+
 ### Issues
 
 #### `list_issues`
@@ -208,6 +183,10 @@ Change work item status.
 List issues (excludes closed by default).
 
 - `team_id`, `status`, `severity`, `type`, `assigned_to_id` (optional): Filters
+- `search` (optional): Text search in title and description
+- `date_from`, `date_to` (optional): Filter by creation date (ISO format, e.g. "2025-01-01")
+- `sort_by` (optional): Sort field (dateCreated, dateUpdated, severity, title)
+- `sort_order` (optional): Sort direction (desc, asc)
 - `limit`, `offset` (optional): Pagination
 
 #### `get_issue`
@@ -238,6 +217,8 @@ Update an existing issue.
 
 List wiki pages.
 
+- `search` (optional): Text search in title and content
+- `date_from`, `date_to` (optional): Filter by last updated date (ISO format, e.g. "2025-01-01")
 - `limit`, `offset` (optional): Pagination
 
 #### `get_wiki_page`
@@ -267,6 +248,8 @@ Update an existing wiki page.
 
 List journal entries.
 
+- `search` (optional): Text search in title and content
+- `date_from`, `date_to` (optional): Filter by entry date (ISO format, e.g. "2025-01-01")
 - `limit`, `offset` (optional): Pagination
 
 #### `get_journal_entry`
@@ -293,6 +276,18 @@ Update an existing journal entry.
 
 ### Comments
 
+#### `list_work_item_comments`
+
+List all comments on a work item.
+
+- `work_item_id` (required): The work item UUID
+
+#### `list_issue_comments`
+
+List all comments on an issue.
+
+- `issue_id` (required): The issue UUID
+
 #### `create_work_item_comment`
 
 Add a comment to a work item.
@@ -315,6 +310,7 @@ List radar items/initiatives (excludes completed by default).
 
 - `team_id` (optional): Filter by team
 - `stage` (optional): Filter by stage (pending, now, next, later, completed)
+- `search` (optional): Text search in title and description
 - `limit`, `offset` (optional): Pagination
 
 #### `get_radar_item`
@@ -324,4 +320,19 @@ Get a specific radar item.
 - `item_id` (required): UUID or reference number
 - `team_id` (optional): Required when using reference number
 
+### Images
+
+#### `upload_image`
+
+Upload an image file from disk and get back a permanent URL for use in markdown content.
+
+- `file_path` (required): Absolute path to an image file (JPEG, PNG, GIF, WebP; max 5MB)
+- `team_id` (optional): Team ID (required for multi-team users)
+
+#### `download_image`
+
+Download and view an image referenced in content fields. Content from work items, issues, wiki pages, journal entries, and comments may contain image references like `![alt](/api/files/images/...)`. Use this tool with that URL path to view the image.
+
+- `image_url` (required): The image URL path (e.g. `/api/files/images/{team}/{filename}`)
+
 </details>

package/dist/apiClient.js

@@ -96,6 +96,32 @@ export class ApiClient {
             throw new Error(`Failed to PATCH ${path}: ${error}`);
         }
     }
+    async getBuffer(path) {
+        const url = `${config.apiUrl}${path}`;
+        try {
+            const response = await fetch(url, {
+                method: 'GET',
+                headers: {
+                    Authorization: `Bearer ${config.apiKey}`,
+                },
+            });
+            if (!response.ok) {
+                const errorText = await response.text();
+                throw new ApiError(response.status, `API error: ${response.statusText} - ${errorText}`);
+            }
+            const arrayBuffer = await response.arrayBuffer();
+            return {
+                buffer: Buffer.from(arrayBuffer),
+                contentType: response.headers.get('content-type') || 'application/octet-stream',
+            };
+        }
+        catch (error) {
+            if (error instanceof ApiError) {
+                throw error;
+            }
+            throw new Error(`Failed to GET buffer ${path}: ${error}`);
+        }
+    }
     async postMultipart(path, buffer, filename, mimeType) {
         const url = `${config.apiUrl}${path}`;
         const boundary = `----FormBoundary${Date.now()}`;

package/dist/client.js

@@ -411,6 +411,12 @@ export class WolfpackClient {
         return this.api.patch(`/journal-entries/${entryId}`, data);
     }
     // Comment methods
+    async listWorkItemComments(workItemId) {
+        return this.api.get(`/work-items/${workItemId}/comments`);
+    }
+    async listIssueComments(issueId) {
+        return this.api.get(`/issues/${issueId}/comments`);
+    }
     async createWorkItemComment(workItemId, data) {
         return this.api.post(`/work-items/${workItemId}/comments`, data);
     }
@@ -424,6 +430,13 @@ export class WolfpackClient {
         const buffer = Buffer.from(base64Data, 'base64');
         return this.api.postMultipart(`/teams/${teamSlug}/upload-image`, buffer, filename, mimeType);
     }
+    /**
+     * Download an image from the MCP images endpoint and return raw base64 + mimeType.
+     */
+    async downloadImage(team, filename) {
+        const { buffer, contentType } = await this.api.getBuffer(`/images/${team}/${filename}`);
+        return { base64: buffer.toString('base64'), mimeType: contentType };
+    }
     close() {
         // No cleanup needed for API client
     }

package/dist/imageProcessor.js

@@ -0,0 +1,21 @@
+const IMAGE_URL_REGEX = /!\[([^\]]*)\]\(\/api\/files\/images\/([^/]+)\/([^)]+)\)/g;
+/**
+ * Processes markdown content to replace image URLs with base64 data URIs.
+ * Failed fetches or oversized images leave the original URL intact.
+ */
+export async function processContentImages(content, client) {
+    if (!content)
+        return content;
+    const matches = [...content.matchAll(IMAGE_URL_REGEX)];
+    if (matches.length === 0)
+        return content;
+    let result = content;
+    for (const match of matches) {
+        const [fullMatch, alt, team, filename] = match;
+        const dataUri = await client.fetchImageAsBase64(team, filename);
+        if (dataUri) {
+            result = result.replace(fullMatch, `![${alt}](${dataUri})`);
+        }
+    }
+    return result;
+}

package/dist/index.js

@@ -271,6 +271,12 @@ const UpdateJournalEntrySchema = z.object({
         .describe('Updated content (markdown). Supports base64-encoded images which will be auto-uploaded.'),
 });
 // Comment schemas
+const ListWorkItemCommentsSchema = z.object({
+    work_item_id: z.string().describe('The work item UUID'),
+});
+const ListIssueCommentsSchema = z.object({
+    issue_id: z.string().describe('The issue UUID'),
+});
 const CreateWorkItemCommentSchema = z.object({
     work_item_id: z.string().describe('The work item UUID'),
     content: z
@@ -294,6 +300,11 @@ const UploadImageSchema = z.object({
         .optional()
         .describe('Team ID (required for multi-team users, use list_teams to get IDs)'),
 });
+const DownloadImageSchema = z.object({
+    image_url: z
+        .string()
+        .describe('The image URL path found in content fields (e.g. "/api/files/images/{team}/{filename}").'),
+});
 // Helper to detect if a work item description contains a plan
 function hasPlan(description) {
     if (!description)
@@ -414,7 +425,8 @@ class WolfpackMCPServer {
                         'Call this before updating to see current content. ' +
                         'WORKFLOW: When asked to work on an item, check its status and follow the required state transitions ' +
                         '(pending→pull first, new→doing, blocked/ready/completed/closed→new→doing, then review when done). ' +
-                        'PLANNING: Check if the description contains a plan (markdown checklist). If not, APPEND one using update_work_progress - preserve all original description text and add your plan below a "---" separator.',
+                        'PLANNING: Check if the description contains a plan (markdown checklist). If not, APPEND one using update_work_progress - preserve all original description text and add your plan below a "---" separator. ' +
+                        'IMAGES: Image references in the description (e.g. `![alt](/api/files/images/...)`) can be viewed using the download_image tool.',
                     inputSchema: {
                         type: 'object',
                         properties: {
@@ -538,7 +550,8 @@ class WolfpackMCPServer {
                 },
                 {
                     name: 'get_radar_item',
-                    description: 'Get a specific radar item (initiative) by ID or refId, including its work items and participants.',
+                    description: 'Get a specific radar item (initiative) by ID or refId, including its work items and participants. ' +
+                        'IMAGES: Image references in the description (e.g. `![alt](/api/files/images/...)`) can be viewed using the download_image tool.',
                     inputSchema: {
                         type: 'object',
                         properties: {
@@ -615,7 +628,8 @@ class WolfpackMCPServer {
                 },
                 {
                     name: 'get_issue',
-                    description: 'Get a specific issue by ID or refId, including comment and attachment counts.',
+                    description: 'Get a specific issue by ID or refId, including comment and attachment counts. ' +
+                        'IMAGES: Image references in the description (e.g. `![alt](/api/files/images/...)`) can be viewed using the download_image tool.',
                     inputSchema: {
                         type: 'object',
                         properties: {
@@ -750,7 +764,8 @@ class WolfpackMCPServer {
                 },
                 {
                     name: 'get_wiki_page',
-                    description: 'Get a specific wiki/documentation page by ID or slug (URL path). Returns full content in markdown.',
+                    description: 'Get a specific wiki/documentation page by ID or slug (URL path). Returns full content in markdown. ' +
+                        'IMAGES: Image references in the content (e.g. `![alt](/api/files/images/...)`) can be viewed using the download_image tool.',
                     inputSchema: {
                         type: 'object',
                         properties: {
@@ -820,7 +835,8 @@ class WolfpackMCPServer {
                 },
                 {
                     name: 'get_journal_entry',
-                    description: 'Get a specific journal/log entry by ID or reference number. Returns full content.',
+                    description: 'Get a specific journal/log entry by ID or reference number. Returns full content. ' +
+                        'IMAGES: Image references in the content (e.g. `![alt](/api/files/images/...)`) can be viewed using the download_image tool.',
                     inputSchema: {
                         type: 'object',
                         properties: {
@@ -866,6 +882,30 @@ class WolfpackMCPServer {
                     },
                 },
                 // Comment tools
+                {
+                    name: 'list_work_item_comments',
+                    description: 'List all comments on a work item. Returns comments in chronological order. Requires mcp:comments:read permission. ' +
+                        'IMAGES: Image references in comments (e.g. `![alt](/api/files/images/...)`) can be viewed using the download_image tool.',
+                    inputSchema: {
+                        type: 'object',
+                        properties: {
+                            work_item_id: { type: 'string', description: 'The work item UUID' },
+                        },
+                        required: ['work_item_id'],
+                    },
+                },
+                {
+                    name: 'list_issue_comments',
+                    description: 'List all comments on an issue. Returns comments in chronological order. Requires mcp:comments:read permission. ' +
+                        'IMAGES: Image references in comments (e.g. `![alt](/api/files/images/...)`) can be viewed using the download_image tool.',
+                    inputSchema: {
+                        type: 'object',
+                        properties: {
+                            issue_id: { type: 'string', description: 'The issue UUID' },
+                        },
+                        required: ['issue_id'],
+                    },
+                },
                 {
                     name: 'create_work_item_comment',
                     description: 'Add a comment to a work item. Requires mcp:comments:create permission. ' +
@@ -923,6 +963,22 @@ class WolfpackMCPServer {
                         required: ['file_path'],
                     },
                 },
+                {
+                    name: 'download_image',
+                    description: 'Download and view an image referenced in content fields. ' +
+                        'Content from work items, issues, wiki pages, journal entries, and comments may contain image references like `![alt](/api/files/images/...)`. ' +
+                        'Use this tool with that URL path to download and view the image.',
+                    inputSchema: {
+                        type: 'object',
+                        properties: {
+                            image_url: {
+                                type: 'string',
+                                description: 'The image URL path found in content fields (e.g. "/api/files/images/{team}/{filename}").',
+                            },
+                        },
+                        required: ['image_url'],
+                    },
+                },
             ],
         }));
         this.server.setRequestHandler(CallToolRequestSchema, async (request) => {
@@ -1324,6 +1380,20 @@ class WolfpackMCPServer {
                         };
                     }
                     // Comment handlers
+                    case 'list_work_item_comments': {
+                        const parsed = ListWorkItemCommentsSchema.parse(args);
+                        const comments = await this.client.listWorkItemComments(parsed.work_item_id);
+                        return {
+                            content: [{ type: 'text', text: JSON.stringify(comments, null, 2) }],
+                        };
+                    }
+                    case 'list_issue_comments': {
+                        const parsed = ListIssueCommentsSchema.parse(args);
+                        const comments = await this.client.listIssueComments(parsed.issue_id);
+                        return {
+                            content: [{ type: 'text', text: JSON.stringify(comments, null, 2) }],
+                        };
+                    }
                     case 'create_work_item_comment': {
                         const parsed = CreateWorkItemCommentSchema.parse(args);
                         const comment = await this.client.createWorkItemComment(parsed.work_item_id, {
@@ -1391,6 +1461,24 @@ class WolfpackMCPServer {
                             ],
                         };
                     }
+                    case 'download_image': {
+                        const parsed = DownloadImageSchema.parse(args);
+                        const match = parsed.image_url.match(/\/api\/files\/images\/([^/]+)\/(.+)$/);
+                        if (!match) {
+                            throw new Error('Invalid image URL. Expected format: /api/files/images/{team}/{filename}');
+                        }
+                        const [, team, filename] = match;
+                        const { base64, mimeType } = await this.client.downloadImage(team, filename);
+                        return {
+                            content: [
+                                {
+                                    type: 'image',
+                                    data: base64,
+                                    mimeType,
+                                },
+                            ],
+                        };
+                    }
                     default:
                         throw new Error(`Unknown tool: ${name}`);
                 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "wolfpack-mcp",
-  "version": "1.0.27",
+  "version": "1.0.29",
   "description": "MCP server for Wolfpack AI-enhanced software delivery tools",
   "main": "dist/index.js",
   "type": "module",