Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
MALAI 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.
What it does
GLP-1 nutrition companion: your food log, protein targets, next meals, plus USDA food facts.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http malai-mcp https://mcp.itsmalai.com/mcp
# 2 — ask your agent for something these tools do
# malai_get_today_nutrition, malai_log_food, malai_suggest_next_meal and 8 more
MALAI costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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.
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 malai-mcp https://mcp.itsmalai.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
11 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.
MALAI: Get what the user has eaten today against their MALAI targets: calories, protein, carbs, fat and fiber eaten vs target, what is left (especially protein), and how many entries are logged. Use for "how am I doing today", "how much protein do I have left", "am I on track", or before suggesting what to eat. These are the user's real logged numbers; do not estimate them.
No parameter schema on file.
MALAI: Log food or drink the user says they ate into their MALAI food log, from their own words, e.g. "2 boiled eggs", "a protein shake", "half my chicken rice bowl". Use whenever the user says they ate, drank, or want to log something. Step 1: call with text only; MALAI returns matching options from its food database and the user's saved recipes. Step 2: confirm the right option with the user (or
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | What the user ate, in their words, e.g. "2 boiled eggs". |
| itemId | string | no | Exact item from an earlier MALAI result (options or logWith). Requires itemType. |
| itemType | string | no | Type of itemId. |
| amount | number | no | How much: number of servings, or grams/ml when unit is g/ml. Defaults to 1 serving. |
| unit | string | no | Unit for amount. Defaults to serving. |
| meal | string | no | Meal time, if the user said it. |
| consumedAt | string | no | When they ate it, ISO 8601. Defaults to now. |
| recommendationId | string | no | Pass through from malai_suggest_next_meal logWith, if logging a suggestion. |
| requestId | string | no | A unique id you create for this log (e.g. a UUID). Send the same id when retrying so the food is never logged twice. |
MALAI: Get personalised ideas for the user's next meal or snack, chosen by MALAI from their saved recipes and MALAI's GLP-1-friendly recipes to close today's protein gap at this time of day. Use for "what should I eat", "what's for dinner", "I'm hungry", "something light with protein". Returns up to 3 options with protein and calories. To log one, call malai_log_food with the values in its logWith
No parameter schema on file.
MALAI: Read what the user actually logged in MALAI across a date range: their real history, not a plan. Use for "what did I eat yesterday", "what did I have this week", "how has my protein been lately". Defaults to the last 7 days. Returns each entry with its entryId, meal and nutrition, and a total.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| startDate | string | no | First day, YYYY-MM-DD, in the user's time zone. Defaults to 6 days before today. |
| endDate | string | no | Last day, YYYY-MM-DD, inclusive. Defaults to today. |
MALAI: Read the user's daily nutrition targets from MALAI: calories, protein, carbs, fat, fiber, plus BMR and TDEE. MALAI calculates these from the user's profile and GLP-1 needs; use them exactly as given rather than calculating your own. Use when the user asks about their goals, their protein target, or whether an amount is enough.
No parameter schema on file.
MALAI: List the recipes and foods the user saved in MALAI, with the meal times each is marked for and per-serving nutrition. Use for "what recipes do I have", "show my saved meals", or to suggest something the user already likes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slot | string | no | Only items the user marked for this meal time. |
| type | string | no | Only recipes or only foods. |
MALAI: Read the user's body profile in MALAI: age, sex, height, weight, activity level, goal and units. Use before advice that depends on their body or goal. If isPlaceholder is true the profile was never filled in; tell the user and suggest completing it in the MALAI app rather than quoting numbers based on it.
No parameter schema on file.
MALAI: Look up nutrition for a food in MALAI's database (USDA FoodData Central, US foods): calories, protein, carbs, fat, fiber, saturated fat and sugar per serving (or per 100 g), plus the share of calories from protein. Use for "how much protein is in cottage cheese", "compare tofu and chicken", "is a turkey sandwich high in protein". A null value means unknown, not zero. Don't use to log food (
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Food name, e.g. "cottage cheese 2%". |
| limit | integer | no | Maximum results, 1–10. Default 5. |
MALAI: Calculate a daily protein range for someone on a GLP-1 medication from their body weight: 1.2–1.6 g per kg, the 2025 joint advisory range for weight loss, split into per-meal amounts. Same method as MALAI's protein calculator. Use for "how much protein should I eat on Zepbound", "I weigh 210 lb, what's my protein target". Don't use for a signed-in user's saved MALAI target (that is malai_ge
| Parameter | Type | Required | Notes |
|---|---|---|---|
| weight | number | yes | Current body weight. |
| weight_unit | string | yes | Unit of weight. |
| meals_per_day | integer | no | Meals to spread protein across. Default 4. |
MALAI: Estimate daily calories, protein, carbs, fat and fiber from sex, age, height, weight, activity and goal, with MALAI's safety limits (a calorie floor and a cap on the rate of loss). Same calculator the MALAI app uses. Use for "how many calories should I eat on Wegovy", "what macros to lose 1 lb a week". Adults only. Don't use for a signed-in user's saved targets (that is malai_get_nutrition_
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sex | string | yes | Sex used by the calorie formula. |
| age | integer | yes | Age in years. Adults only (18+). |
| height | number | yes | Height, in height_unit. Feet and inches must be converted to inches (5 ft 6 in = 66). |
| height_unit | string | yes | Unit of height. |
| weight | number | yes | Current body weight, in weight_unit. |
| weight_unit | string | yes | Unit of weight and of rate_per_week. |
| activity | string | no | Daily activity: sedentary (desk, little exercise), light (1–3 workouts a week), moderate (3–5), very_active (6–7), athlete (training twice a day). Default light. |
| goal | string | no | Weight goal. Default lose. |
| rate_per_week | number | no | Desired change per week, in weight_unit. Ignored for maintain. Default 0.5 kg (1.1 lb). Loss is capped for safety; the applied rate is returned as rate_per_week_kg. |
MALAI: Get MALAI's guide to a GLP-1 medication (Ozempic, Wegovy, Mounjaro or Zepbound): dose steps, common side effects with trial frequencies and food tips, what to eat, treatment phases, the first week, and FAQs, citing prescribing information. Use for "what are Mounjaro side effects", "what should I eat in my first week on Wegovy". Never use it to recommend a dose change, skipping or stopping;
| Parameter | Type | Required | Notes |
|---|---|---|---|
| medication | string | yes | Brand name. Semaglutide is Ozempic/Wegovy; tirzepatide is Mounjaro/Zepbound. |
| sections | array | no | Default: overview, doses, side_effects, nutrition. |
- 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 MALAI or to call it, at any volume.
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.
| 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 |
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.
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 |
|---|---|---|
| malai_get_today_nutrition | no tags | |
| malai_log_food | state-write | state-write: declares readOnlyHint: false |
| malai_suggest_next_meal | no tags | |
| malai_get_food_log | no tags | |
| malai_get_nutrition_targets | no tags | |
| malai_get_saved_recipes | no tags | |
| malai_get_body_profile | no tags | |
| malai_search_foods | no tags | |
| malai_calculate_protein_target | no tags | |
| malai_calculate_daily_targets | no tags | |
| malai_get_medication_guide | 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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
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 1.1.0.
No release note was published with this version.
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.
Any signed-in account that does not publish MALAI can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.