Visitor takeaway
52/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.

by VoiceBit Inc.(Community)
Visitor takeaway
52/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Needs category
This listing is missing a primary category, which weakens browse placement and AI recommendation routing.
Connector evidence
Reachable
Tedix can reach this MCP endpoint and can show live capability evidence when tools are discovered.
Directory freshness
23h ago
Catalog metadata was refreshed 23h ago (June 23, 2026).
This app helps user find and order their favorite food from local restaurants who are on VoiceBit platform
No special capabilities listed
VoiceBit is indexed by Tedix as a structured ai application listing for AI assistants, search crawlers, and users comparing agent-ready apps.
Use this page to understand whether VoiceBit is relevant for general AI app workflows in AI assistants.
For MCP discovery, this listing helps crawlers connect VoiceBit to tool, resource, prompt, and server-health signals instead of treating it as a generic directory entry.
The canonical Tedix directory URL is https://tedix.dev/apps/voicebit/.
Tedix identifies VoiceBit from Upstream Mcp tool source; Store sources: ChatGPT app store; Distribution: Ecosystem Directory; Tenant install: A platform catalog operator must create or reconcile the base app before tenants can install this entry.. Availability is reported for US.
Authentication: Open Access. No special capability flags are currently listed. Current MCP inventory reports 11 tools, 3 resources, and 0 prompts.
Add a menu item line to an existing cart. Identify the item by its display name from get_menu. Variant and modifiers are matched by name within the resolved item.
Empty the cart entirely. Drops every line and invalidates the cart_id; a fresh create_cart is required if the user wants to start over.
Create a new empty cart bound to a restaurant slug. Returns a cart_id you must carry across all subsequent cart and submit_order calls in this conversation.
Fetch a restaurant's menu as structured data for agent reasoning and filtering. By default this returns categories, items, and variants only; set include_modifiers=true only when the user explicitly asks about customization choices. For filtered ChatGPT UI requests such as vegetarian pizzas, use this to identify matching items, answer with the matching text summary, then call render_restaurant_detail with slug plus item_names or item_ids for only those matches.
Fetch a single restaurant's profile (hours, service methods, ordering status) as structured data. For broad ChatGPT UI display flows, prefer render_restaurant_detail with the slug. For filtered menu flows, pair the slug with get_menu and pass only selected item_names/item_ids to render_restaurant_detail.
Remove (or decrement) a previously-added line. Without `qty`, removes the most recent matching line entirely; with `qty`, decrements that quantity. Removing the last line keeps the cart_id valid — add more items, or call submit_order, or clear_cart to reset.
User-facing ChatGPT UI renderer for restaurant search results. Use this after search_restaurants whenever restaurants should be displayed to the user. This is the final display step for show, list, browse, or view restaurant requests.
User-facing ChatGPT UI renderer for selected restaurant menu items. For filtered requests like vegetarian pizzas, first use get_menu to find matching items, answer with a concise text summary, then call this with slug plus item_names or item_ids for only those matching items. The server hydrates the selected items with variants/modifiers for the iframe. Do not call this with only a slug for filtered requests; slug-only calls render the broad menu and should be used only when the user explicitly asks for the whole restaurant menu. This surface is read-only for discovery; use add_to_cart/view_cart renderers for cart state and ordering.
Plus 3 additional actions in the full tool inventory.
Public trust signals for visitors and practical recommendations for publishers. Use this section to understand what Tedix can verify today and what would make the app easier for AI agents to find.
Visitor takeaway
52/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Needs category
This listing is missing a primary category, which weakens browse placement and AI recommendation routing.
Connector evidence
Reachable
Tedix can reach this MCP endpoint and can show live capability evidence when tools are discovered.
Directory freshness
23h ago
Catalog metadata was refreshed 23h ago (June 23, 2026).
MCP list method errors: resourceTemplates: RPC error -32601: Method not found; prompts: RPC error -32601: Method not found
https://eat.voicebit.ai/api/mcpLast checked: June 16, 2026
VoiceBit restaurant marketplace tools. This connector supports embedded ChatGPT UI. For user-facing browsing or display requests, prefer render methods over raw JSON/text responses. JSON/data methods are intermediate agent-only calls unless no matching render method exists. Browse restaurants and menus, build a cart with add_to_cart / remove_from_cart, and place a real order with submit_order (which will redirect the user to a payment page). Always pass the same cart_id once create_cart returns one. When the user asks to show, list, browse, or view restaurants, call search_restaurants first, then immediately call render_restaurant_carousel with the returned restaurants before replying. For filtered menu requests such as vegetarian pizzas, call get_menu, explain the matching items in text, then call render_restaurant_detail with slug plus item_names or item_ids for only those matching items. Do not render the whole menu for filtered requests. Use render_restaurant_detail with only a slug when the user explicitly asks to browse the full restaurant menu.
MCP list method errors: resourceTemplates: RPC error -32601: Method not found; prompts: RPC error -32601: Method not found
Showing 11 of 11 tools
| Tool | Description | Flags | Test | Last Tested | |
|---|---|---|---|---|---|
add_to_cart | Add a menu item line to an existing cart. Identify the item by its display name from get_menu. Variant and modifiers are matched by name within the resolved item. | — | 100%Latency 1.3s | 3d ago | |
clear_cart | Empty the cart entirely. Drops every line and invalidates the cart_id; a fresh create_cart is required if the user wants to start over. | — | 100%Latency 502ms | 3d ago | |
create_cart | Create a new empty cart bound to a restaurant slug. Returns a cart_id you must carry across all subsequent cart and submit_order calls in this conversation. | — | 100%Latency 732ms | 3d ago | |
get_menu | Fetch a restaurant's menu as structured data for agent reasoning and filtering. By default this returns categories, items, and variants only; set include_modifiers=true only when the user explicitly asks about customization choices. For filtered ChatGPT UI requests such as vegetarian pizzas, use this to identify matching items, answer with the matching text summary, then call render_restaurant_detail with slug plus item_names or item_ids for only those matches. | read-only | 100%Latency 664ms | 3d ago | |
get_restaurant | Fetch a single restaurant's profile (hours, service methods, ordering status) as structured data. For broad ChatGPT UI display flows, prefer render_restaurant_detail with the slug. For filtered menu flows, pair the slug with get_menu and pass only selected item_names/item_ids to render_restaurant_detail. | read-only | 100%Latency 511ms | 3d ago | |
remove_from_cart | Remove (or decrement) a previously-added line. Without `qty`, removes the most recent matching line entirely; with `qty`, decrements that quantity. Removing the last line keeps the cart_id valid — add more items, or call submit_order, or clear_cart to reset. | — | 100%Latency 379ms | 3d ago | |
render_restaurant_carousel | User-facing ChatGPT UI renderer for restaurant search results. Use this after search_restaurants whenever restaurants should be displayed to the user. This is the final display step for show, list, browse, or view restaurant requests. | read-only | 100%Latency 2.5s | 2d ago | |
render_restaurant_detail | User-facing ChatGPT UI renderer for selected restaurant menu items. For filtered requests like vegetarian pizzas, first use get_menu to find matching items, answer with a concise text summary, then call this with slug plus item_names or item_ids for only those matching items. The server hydrates the selected items with variants/modifiers for the iframe. Do not call this with only a slug for filtered requests; slug-only calls render the broad menu and should be used only when the user explicitly asks for the whole restaurant menu. This surface is read-only for discovery; use add_to_cart/view_cart renderers for cart state and ordering. | read-only | 100%Latency 622ms | 2d ago | |
search_restaurants | Fetch VoiceBit-marketplace restaurants as structured data. This is an agent-only intermediate method for ChatGPT UI flows. Optional case-insensitive substring filter on name and cuisine. When the user asks to show, list, browse, or view restaurants, you must immediately call render_restaurant_carousel with the returned restaurants before replying to the user. | read-only | 100%Latency 1.4s | 2d ago | |
submit_order | Submit the cart as a real order. Collects customer name + phone (no account required) and forwards to the VoiceBit ordering backend. Returns an order_id and a redirect_url to the checkout app where the user completes payment. THIS PLACES A REAL ORDER — confirm with the user before calling. | destructive | 100%Latency 448ms | 2d ago | |
view_cart | Read the current contents of a cart by cart_id. Returns line items, totals, and any pre-set service method or schedule. | read-only | 100%Latency 450ms | 2d ago |
Fair
52 of 100 — how easily AI agents can find this app
Add at least 2 example prompts. Prompt examples strongly improve app matching and click-through intent.
Increase keyword coverage (discovery + trigger) to improve retrieval for long-tail queries.
Choose a primary catalog category so visitors and AI agents can route this app into the right browse and recommendation surfaces.
Add at least 2 screenshots that show real workflows to increase confidence and conversion.