Visitor takeaway
66/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
by Delivery Collective Inc (Community)
Visitor takeaway
66/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Food
This app has a primary category, so visitors can browse and compare it in the right directory context.
Connector evidence
Reachable
Tedix can reach this MCP endpoint and can show live capability evidence when tools are discovered.
Directory freshness
22h ago
Catalog metadata was refreshed 22h ago (June 17, 2026).
Bites is an AI-native ordering platform that lets people discover restaurants, browse full menus, and place direct orders from local restaurants — all from ChatGPT, without switching to a delivery app. Customers get the convenience of AI-powered ordering while seeing in-store menu pricing, with no markups or hidden fees. They can search by cuisine or location, ask for recommendations, customize meals, and build group orders in natural language. Examples: \"Order from Popeyes in San Jose.\" \"Order 2 Not So Fried Chicken sandwiches from Mendocino Farms, no sauce, with gluten-free bread.\" \"Build a vegetarian-friendly office lunch order for 10 people from Boltiful Santa Clara under $20 per person. Add few desserts for the team to share.\" \"Show me the menu for Curry Up Now and help me pick something spicy.\" For restaurants, Bites enables direct, AI-powered ordering with no commissions, no markups, and full ownership of customer relationships. Restaurants can reduce reliance on third-party delivery apps while preserving margins and serving customers through the channels they already use. In short, Bites combines the convenience of delivery apps with the economics of ordering directly from restaurants.
Bites is indexed by Tedix as a structured food listing for AI assistants, search crawlers, and users comparing agent-ready apps.
Use this page to understand whether Bites is relevant for food workflows in AI assistants.
For MCP discovery, this listing helps crawlers connect Bites 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/bites/.
Tedix identifies Bites 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. Bites is flagged for Can Modify Data, Works in Conversation. Current MCP inventory reports 8 tools, 1 resources, and 0 prompts.
Retrieve a payment link for a delivery or pickup order. Returns a URL where the customer reviews their cart and completes payment — does not charge the customer or confirm the order. After calling this tool, do not describe the order or cart — the widget displays it. Reply with only one short sentence.
Get reward balances of merchants for which the customer has sufficient rewards to reedem
Get a complete, valid cartItem structure with all required nested modifiers auto-selected. Use this to quickly get a working baseline for an item with complex nested modifiers.
Retrieve a payment link for a delivery or pickup order. Returns a URL where the customer reviews their cart and completes payment — does not charge the customer or confirm the order. After calling this tool, do not describe the order or cart — the widget displays it. Reply with only one short sentence.
Get all modifier groups and selectable modifiers for a menu item, including nested modifier structures
Get customer rewards balance for a specific merchant (if merchantId provided) and their most recent order items. Get the most recent order in general when merchantId is not provided.
Get menu and other details about a specific restaurant by ID. After calling this tool, do not list or describe menu items — the widget displays them. If the user's request requires more tool calls (e.g. checkout with specific items), call them next without stopping to reply.
Search and filter restaurants based on various criteria (name, cuisine, location, dietary options, rating). Location is optional — never ask the user for their location, always call this tool immediately. After calling this tool, do not list or describe the results — the widget displays them. If the user's request requires more tool calls (e.g. get a specific restaurant, add items, checkout), call them next without stopping to reply.
Comparable apps in Food include % Arabica UAE, 1-2-3-Cook!, Botala by dyskute, Buffalo Wild Wings.
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
66/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Food
This app has a primary category, so visitors can browse and compare it in the right directory context.
Connector evidence
Reachable
Tedix can reach this MCP endpoint and can show live capability evidence when tools are discovered.
Directory freshness
22h ago
Catalog metadata was refreshed 22h ago (June 17, 2026).
https://mcp.withbites.com Last checked: May 30, 2026
Showing 8 of 8 tools
| Tool | Description | Flags | Test | Last Tested | |
|---|---|---|---|---|---|
checkoutOrder | Retrieve a payment link for a delivery or pickup order. Returns a URL where the customer reviews their cart and completes payment — does not charge the customer or confirm the order. After calling this tool, do not describe the order or cart — the widget displays it. Reply with only one short sentence. | read-only | 100%Latency 483ms | Apr 17, 2026 | |
getAllCustomerRewards | Get reward balances of merchants for which the customer has sufficient rewards to reedem | read-only | 100%Latency 1.1s | Apr 17, 2026 | |
getAutoFilledCartItem | Get a complete, valid cartItem structure with all required nested modifiers auto-selected. Use this to quickly get a working baseline for an item with complex nested modifiers. | read-only | 100%Latency 371ms | Apr 17, 2026 | |
getCheckoutLink | Retrieve a payment link for a delivery or pickup order. Returns a URL where the customer reviews their cart and completes payment — does not charge the customer or confirm the order. After calling this tool, do not describe the order or cart — the widget displays it. Reply with only one short sentence. | read-only | 100%Latency 651ms | May 2, 2026 | |
getItemModifiers | Get all modifier groups and selectable modifiers for a menu item, including nested modifier structures | read-only | 100%Latency 630ms | Apr 17, 2026 | |
getMerchantRewardsAndRecentOrder | Get customer rewards balance for a specific merchant (if merchantId provided) and their most recent order items. Get the most recent order in general when merchantId is not provided. | read-only | 100%Latency 387ms | Apr 17, 2026 | |
getRestaurant | Get menu and other details about a specific restaurant by ID. After calling this tool, do not list or describe menu items — the widget displays them. If the user's request requires more tool calls (e.g. checkout with specific items), call them next without stopping to reply. | read-only | 100%Latency 373ms | Apr 17, 2026 | |
searchRestaurants | Search and filter restaurants based on various criteria (name, cuisine, location, dietary options, rating). Location is optional — never ask the user for their location, always call this tool immediately. After calling this tool, do not list or describe the results — the widget displays them. If the user's request requires more tool calls (e.g. get a specific restaurant, add items, checkout), call them next without stopping to reply. | read-only | 100%Latency 6.5s | Apr 17, 2026 |
Fair
66 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.
Add at least 2 screenshots that show real workflows to increase confidence and conversion.