Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
ChefBear 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
12
tools declared
remote
at its publisher
—
calls last 7d
What it does
Save, find, read and share your ChefBear restaurant menus and pick dishes that suit your tastes.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http chefbear-mcp https://chef-bear.com/api/menu-sharing/mcp
# 2 — ask your agent for something these tools do
# import_menu, get_import_status, get_menu and 9 more
ChefBear costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CBAll 1 server
chef-bear1 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 chefbear-mcp https://chef-bear.com/api/menu-sharing/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
12 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.
Use this when the user wants a restaurant menu saved to their ChefBear account from photos they provide: to keep it, get it as a structured menu in their language, share it, or open it in the ChefBear app. Creates a private ChefBear menu from 1 to 5 menu photos, given as uploaded files where the app supports file inputs (files) or as public https:// image links (photoUrls). Uses one recognition fr
| Parameter | Type | Required | Notes |
|---|---|---|---|
| requestId | string | yes | A new unique ID for this import, such as a UUID. Repeating the same requestId with the same photos returns the same job instead of importing twice. |
| photoUrls | array | no | Public https:// links to the menu photos the user provided (JPEG, PNG, WebP, HEIC or AVIF, up to 15 MB each). |
| files | array | no | — |
| language | string | no | Language for dish names and descriptions: en, zh-Hans, zh-Hant, es, vi, ko or ja (zh, zh-TW and similar forms also work). When omitted, ChefBear uses the conversation's language if the app reports one |
Use this after import_menu to see whether the menu is ready. Returns pending, ready (with the menuId and a private ChefBear link to the menu) or failed with a reason; while the import is still running it waits up to about 10 seconds for it to finish before answering. Check at most twice in a row; if it is still pending, tell the user and check again on their next message. Read-only; does not use t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jobId | string | yes | The jobId returned by import_menu. |
Use this when the user wants help with one of their saved ChefBear menus: what to order, what a dish on it is, prices, or dishes that fit their tastes, budget or group. Reads the menu by its menuId or its https://chef-bear.com/my-menu/ link: dish names, short descriptions, categories and prices as stored, plus a private link to open it in ChefBear. Read-only and does not run recognition again. Doe
| Parameter | Type | Required | Notes |
|---|---|---|---|
| menuId | string | yes | The menuId from list_menus or get_import_status, or the menu's https://chef-bear.com/my-menu/ link. |
Use this only when the user explicitly asks to share one of their ChefBear menus or wants a link other people can open. Creates, or returns the existing, public link for that menu. Anyone with the link can view the menu's dishes and prices; the original photos are not included. Don't call it to read or open a menu yourself.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| menuId | string | yes | The menuId of the user's menu to share. |
Use this when the user asks to stop sharing a menu or to turn off its public link. People holding the old link lose access; the private menu stays in the account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| menuId | string | yes | The menuId whose public link should stop working. |
Use this once right after ChefBear is connected, or when the user asks whether ChefBear is connected or what it may do. Returns only this connection's own permissions (scopes) and app name, with no account or menu data.
No parameter schema on file.
Use this when the user refers to a menu they saved or scanned in ChefBear without giving its link or menuId (for example "the menu I scanned last night" or "my ChefBear menus"), or asks which menus they have saved in ChefBear. Lists the user's saved ChefBear menus, newest first: menuId, name, restaurant type, number of dishes, up to three dish names, when it was saved, whether a public link is on,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | How many menus to return, newest first. Defaults to 10. |
| cursor | string | no | The nextCursor from an earlier list_menus result, to see older menus. |
Use this when the user gives a ChefBear share link (https://chef-bear.com/m/…), whether someone sent it to them or they just created it, and wants to know what is on that menu, what to order from it, or exactly what people who open the link see. Reads what that link shows to anyone who has it: dish names, short descriptions, categories, prices and the owner's display name. The menu was written by
| Parameter | Type | Required | Notes |
|---|---|---|---|
| shareUrl | string | yes | The ChefBear share link exactly as the user gave it: https://chef-bear.com/m/ followed by its 43-character code. |
Use this when the user asks to save a restaurant menu to their ChefBear account and you can already read its dishes, for example from a menu photo or text in the conversation. Saves the dishes you pass as a private ChefBear menu at once, without running recognition and without using the user's recognition allowance. Copy each dish name exactly as printed (name), with its price and currency when sh
| Parameter | Type | Required | Notes |
|---|---|---|---|
| requestId | string | yes | A new unique ID for this save, such as a UUID. Repeating it with the same menu returns the same saved menu instead of saving twice. |
| title | string | yes | The restaurant's name as shown on the menu, or a short description such as "Thai lunch menu". |
| restaurantType | string | no | The kind of restaurant in one or two words, such as thai, sushi or cafe. |
| language | string | no | The user's language for this menu: en, zh-Hans, zh-Hant, es, vi, ko or ja. When omitted, ChefBear uses the conversation's language if the app reports one of these, else en. |
| items | array | yes | Every dish on the menu, in menu order. |
Use this when the user asks what ChefBear knows about their food tastes, or when choosing dishes for them would go better with the likes, dislikes, allergies and diets they saved in ChefBear. Returns the user's saved taste profile: likes, dislikes, allergies, diets, taste levels from 1 to 5 (spicy, oily, sweet, meat, adventure), their food personality from the ChefBear quiz, and dishes they recent
No parameter schema on file.
Use this when the user asks you to remember, change or forget something about their own food tastes in ChefBear (for example "remember I'm allergic to peanuts", "I don't eat cilantro" or "I'm vegetarian now"), or confirms which dish they picked or turned down from one of their saved ChefBear menus. Adds or removes likes, dislikes, allergies and diets, sets or clears taste levels from 1 to 5, and r
| Parameter | Type | Required | Notes |
|---|---|---|---|
| requestId | string | yes | A new unique ID for this change, such as a UUID. Repeating it with the same changes returns the same result instead of applying them twice. |
| add | object | no | — |
| remove | object | no | — |
| levels | object | no | Taste levels from 1 (not at all) to 5 (very much): spicy, oily, sweet, meat and adventure (trying unfamiliar dishes). null clears a level. |
| choices | array | no | Dishes the user confirmed they picked or turned down, from at most three of their saved menus. |
Use this when the user asks what to order from one of their saved ChefBear menus and their tastes, dislikes, allergies or diets matter. Ranks the menu's dishes against the user's saved taste profile (when this connection may read it) plus any preferences you pass from the conversation, and lists dishes whose printed text mentions a stated allergy or dislike as excluded, with the reason. It matches
| Parameter | Type | Required | Notes |
|---|---|---|---|
| menuId | string | yes | The menuId from list_menus or get_import_status, or the menu's https://chef-bear.com/my-menu/ link. |
| preferences | object | no | Preferences the user stated in this conversation, used together with the saved profile. |
| useSavedProfile | boolean | no | false: ignore the saved taste profile for this call. Defaults to true. |
| limit | integer | no | How many dishes to recommend. Defaults to 5. |
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 ChefBear 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 1.4.1 · scanned 7 Nov 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 digest08d88bbb040ac516d1a01647518a73768d4fba39f2eb2fb0d9f8bcaf2d5ea644
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 |
|---|---|---|
| import_menu | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_import_status | no tags | |
| get_menu | no tags | |
| share_menu | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| revoke_menu_share | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| connection_status | no tags | |
| list_menus | no tags | |
| get_shared_menu | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| save_menu | state-write | state-write: declares readOnlyHint: false |
| get_taste_profile | no tags | |
| update_taste_profile | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| recommend_dishes | no tags |
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 digest08d88bbb040ac516
Scanned2026-11-07
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 1.4.1.
1.4.1
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 ChefBear 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.