# fetch_images_for_alt_fill One-shot helper for filling image_alt across the site. Returns image bytes + element metadata in a single response so Claude can describe everything in one pass, then call set_image_alts once. Workflow: 1. Call this tool with scope/limit. 2. Tool returns each image inline with its element_id + source_type + source_id. 3. Claude reads images, drafts an alt for each, then calls set_image_alts(items) once with the template at the end of the response. The pre-built Agent View of the PolicyLayer registry record for `fetch_images_for_alt_fill`. HTML page: https://policylayer.com/tools/webcake-storefront/fetch-images-for-alt-fill ## Facts - Tool: `fetch_images_for_alt_fill` - Server: Webcake Storefront (`webcake-storefront-mcp`) — https://policylayer.com/tools/webcake-storefront.md - Install: `npx -y webcake-storefront-mcp` - Homepage: git+https://github.com/vuluu2k/webcake-storefront-mcp.git - Risk category: Read (Low risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Allowed ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "fetch_images_for_alt_fill", "arguments": {} } } ``` ## Why fetch_images_for_alt_fill is rated Low This tool retrieves image data and metadata for display and inspection purposes. It has no side effects, cannot modify data, and explicitly delegates any mutations to a separate 'set_image_alts' tool. This is a straightforward Read operation with low blast radius if misused—worst case, an agent could fetch images, but cannot alter the storefront without invoking the distinct Write tool. From the tool's own definition: "Tool name uses 'fetch_' verb and description states it 'returns image bytes + element metadata' with no mutation capability. Workflow step 1 says 'Call this tool with scope/limit' and step 2 says 'Tool returns each image' — purely retrieval operations." ## Use case AI agents call fetch_images_for_alt_fill to retrieve information from Webcake Storefront without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere. ## Recommended policy (PolicyLayer) Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Webcake Storefront: ```json { "version": "1", "default": "deny", "tools": { "fetch_images_for_alt_fill": {} } } ``` ## Other tools on Webcake Storefront (286) - `clear_page_draft` — Destructive — https://policylayer.com/tools/webcake-storefront/clear-page-draft.md - `delete_affiliate_accounts` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-affiliate-accounts.md - `delete_affiliate_products` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-affiliate-products.md - `delete_appointment_addresses` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-appointment-addresses.md - `delete_appointment_calendars` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-appointment-calendars.md - `delete_appointment_classifies` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-appointment-classifies.md - `delete_appointment_employees` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-appointment-employees.md - `delete_article` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-article.md - `delete_automation` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-automation.md - `delete_collection` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-collection.md - `delete_contacts` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-contacts.md - `delete_course` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-course.md - `delete_courses` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-courses.md - `delete_domain` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-domain.md - `delete_employees` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-employees.md - `delete_global_section` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-global-section.md - `delete_global_source` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-global-source.md - `delete_page` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-page.md - `delete_partner_feeds` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-partner-feeds.md - `delete_product` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-product.md - `delete_product_category` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-product-category.md - `delete_redirect_urls` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-redirect-urls.md - `delete_saved_filter` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-saved-filter.md - `delete_site_utms` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-site-utms.md - `delete_subscribers` — Destructive — https://policylayer.com/tools/webcake-storefront/delete-subscribers.md - `empty_media_trash` — Destructive — https://policylayer.com/tools/webcake-storefront/empty-media-trash.md - `remove_font` — Destructive — https://policylayer.com/tools/webcake-storefront/remove-font.md - `remove_font_group` — Destructive — https://policylayer.com/tools/webcake-storefront/remove-font-group.md - `remove_reviews` — Destructive — https://policylayer.com/tools/webcake-storefront/remove-reviews.md - `unblock_all_phone_customers` — Destructive — https://policylayer.com/tools/webcake-storefront/unblock-all-phone-customers.md - …and 256 more: https://policylayer.com/tools/webcake-storefront.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=webcake-storefront · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/webcake-storefront