Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Lezzoo is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
21
tools declared
remote
at its publisher
—
calls last 7d
What it does
Order food, groceries & pharmacy delivery in Kurdistan & Iraq: search, menus, cart, checkout.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http lezzoo-mcp https://mcp.lezzoo.com/mcp
# 2 — ask your agent for something these tools do
# search, search_merchant_products, get_full_menu and 18 more
Lezzoo costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
LEAll 1 server
lezzoo1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http lezzoo-mcp https://mcp.lezzoo.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
21 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search Lezzoo for restaurants/stores near a location. Results are ranked by relevance and proximity, so location matters: pass the user's latitude/longitude when known. If location is unknown, the user's area/address can be used to derive it; otherwise a configured default location applies. Returns restaurants as cards (when the host supports MCP Apps). Use a returned merchant's merchant_id with
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Free-text search term, e.g. 'burger', 'pharmacy', 'pizza'. |
| latitude | number | no | User latitude (-90..90). Ask the user if unknown; falls back to the server default. |
| longitude | number | no | User longitude (-180..180). Falls back to the server default. |
| city | string | no | City to scope results. Defaults server-side. |
| language | string | no | Result language: en, ar, kr, bd. |
| departmentId | integer | no | Optional department id to scope to one vertical (e.g. Food, Grocery, Pharmacy). |
| page | integer | no | 1-based result page (default 1). |
Show the menu for a merchant/restaurant by merchant_id (from a search result). The result includes the menu's categories (sections); pass a categoryId to browse that section's items (paged via page, with has_more). Omit both to show the top items; provide query to search within the menu. Renders as cards with category tabs and Prev/Next when the host supports MCP Apps. Results are pagi
| Parameter | Type | Required | Notes |
|---|---|---|---|
| merchantId | integer | yes | Merchant id, e.g. from a search result's merchant_id. |
| categoryId | integer | no | Menu section id (from the result's categories) to browse. |
| query | string | no | Optional search term within this merchant; omit for the menu. |
| city | string | no | City scope. Defaults server-side. |
| language | string | no | Result language: en, ar, kr, bd. |
| page | integer | no | 1-based page within the category (default 1). |
Fetch the entire menu of a merchant in one call — all categories and all items. Use this when the user wants to browse the full menu, or when you need to find an item across all sections without paging. Returns every category with its products. Capped at 250 items total; if truncated, use search_merchant_products with query= to find specific items.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| merchantId | integer | yes | Merchant id (from a search result's merchant_id). |
| language | string | no | Result language: en, ar, kr, bd. |
Show full details for a single product/menu item by product_id (obtain it from a search_merchant_products result). Returns the image, description, price/discount, stock, and addon options (sizes, extras, toppings) with their prices — rendered as a card when the host supports MCP Apps. Call this when the user taps a product or asks about a specific item.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| productId | integer | yes | Product id, e.g. from a search_merchant_products result's product_id. |
| language | string | no | Result language: en, ar, kr, bd. |
Return the platform's currently trending / most-searched terms. Useful for suggesting what users can look for. Takes no arguments.
No parameter schema on file.
Return whether the customer is signed in for this session, and who.
No parameter schema on file.
Sign the customer out of this session (clears the stored token).
No parameter schema on file.
Return the signed-in customer's profile (name, phone, email, language, loyalty tier, total orders, member-since). Requires the customer to be signed in for this session. Read-only.
No parameter schema on file.
Return the signed-in customer's saved delivery addresses (title, details, type, coordinates). Requires the customer to be signed in for this session. Read-only.
No parameter schema on file.
Return the signed-in customer's orders — current (in-progress) and history (past), each with merchant, status, total, item count and date. Requires the customer to be signed in for this session. Read-only.
No parameter schema on file.
Track a Lezzoo order live — status, ETA, driver name/status/location, merchant, destination, and the ordered items (name, description, quantity, price, chosen options, image) — rendered as a status card with a progress stepper (and a map when the driver's live position is available). Pass an order_id, or omit it to track the customer's most recent active order. Requires sign-in. Read-only. Call ag
| Parameter | Type | Required | Notes |
|---|---|---|---|
| orderId | integer | no | Order id to track. Omit to track the most recent active order. |
Show the current shopping cart (items, options, quantities, line prices, subtotal). Anonymous — no sign-in required. Read-only.
No parameter schema on file.
Add one or more products to the cart in a single call (put a whole request's items in one call). For several of the SAME item use quantity (e.g. "2 Chili Boxes" → quantity: 2). For DIFFERENT products use items (an array of { productId, quantity?, optionValueIds? }), each with its own quantity. For a single product, pass productId/quantity/optionValueIds directly. product_id comes from
| Parameter | Type | Required | Notes |
|---|---|---|---|
| items | array | no | Add multiple items in one call. |
| productId | integer | no | Single product id to add (when not using items). |
| quantity | integer | no | Quantity for the single product (default 1). |
| optionValueIds | array | no | Option value ids for the single product. |
| language | string | no | Language for item names (en, ar, kr, bd). |
Set the quantity of a cart line by line_id (from view_cart). Quantity 0 removes it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lineId | string | yes | line_id from view_cart. |
| quantity | integer | yes | New quantity (0 removes). |
Remove a cart line by line_id (from view_cart).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lineId | string | yes | line_id from view_cart. |
Remove all items from the cart.
No parameter schema on file.
List the available DIGITAL payment methods for checkout (e.g. Lezzoo Pay wallet, FIB, Card, Asia Pay, FastPay, Qi Card, NassWallet). Cash on delivery is NOT supported. Requires sign-in. Use this to map a payment method the user names to its payment_type_id.
No parameter schema on file.
Get the current Lezzoo Pay (wallet) balance for the signed-in customer. Requires sign-in.
No parameter schema on file.
Prices the current cart for checkout (delivery, discount, fees, total) and renders an interactive widget in which the user selects their delivery address and payment method as tappable options — those details are chosen in the widget rather than in chat. Use when the user is ready to check out. Requires sign-in and a non-empty cart. Places no order.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paymentTypeId | integer | no | Optional — the user picks this in the widget; defaults to Lezzoo Pay wallet for the initial price. |
| addressId | integer | no | Optional — the user picks this in the widget; defaults to the first saved address in the merchant's city. |
| voucherCode | string | no | Voucher/promo code to apply. |
Place the order from the current cart. Call review_order first so the customer can confirm the total. Set confirm:true to actually place the order — without it, this returns a preview only. Requires sign-in and a non-empty cart.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| confirm | boolean | yes | Must be true to place the order. If false, returns a preview (same as review_order). |
| paymentTypeId | integer | yes | Payment method ID (from get_payment_methods). |
| addressId | integer | no | Address ID to deliver to. Defaults to your first saved address. |
| voucherCode | string | no | Voucher/promo code to apply. |
| confirmActiveOrder | boolean | no | Set true to place even though you have an active order — only after the user acknowledges. |
Generate a payment link for a placed order. Use this if the payment link expired or was not returned at order placement. Requires sign-in.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| orderId | integer | yes | The order ID returned by place_order. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Lezzoo or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 0.15.0 · scanned 30 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest72e0c109851ddb8ff6ca670aa49d869f28070e07100a577c45062a11bae5b589
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_merchant_products | untrusted-input | untrusted-input: keyword "browse", declares openWorldHint: true (interacts with entities outside the server) |
| get_full_menu | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| get_product_details | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_top_searches | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| auth_status | no tags | |
| logout | no tags | |
| get_profile | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_addresses | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_order_history | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| track_order | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| view_cart | no tags | |
| add_to_cart | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| update_cart_item | state-write | state-write: declares readOnlyHint: false |
| remove_cart_item | state-write | state-write: declares readOnlyHint: false |
| clear_cart | state-write | state-write: declares readOnlyHint: false |
| get_payment_methods | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_wallet_balance | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| review_order | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| place_order | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| get_payment_link | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest72e0c109851ddb8f
Scanned2026-10-30
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.15.0.
0.15.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Lezzoo can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.