Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
ReelsMeals 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
16
tools declared
remote
at its publisher
—
calls last 7d
What it does
Find free public recipes; import links and plan meals from your cookbook. Private tools need a plan.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http reelsmeals-mcp https://reelsmeals.com/api/mcp
# 2 — ask your agent for something these tools do
# search_public_recipes, get_public_recipe, get_reelsmeals_setup and 13 more
ReelsMeals costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JMAll 1 server
jmqcooper1 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 reelsmeals-mcp https://reelsmeals.com/api/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
16 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 someone wants a recipe, cooking inspiration or an existing recipe from a creator, without an account. Searches published ReelsMeals recipes. For the user's own saved recipes use search_my_cookbook instead. Never treats public results as the user's cookbook.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Dish, ingredient, creator or cooking style |
| limit | integer | no | — |
Use this after search_public_recipes to read published ingredients and instructions. Cite reelsmealsUrl and the original creator/source. Does not read a private cookbook and does not invent missing steps or quantities.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The slug returned by search_public_recipes |
Use this when the user asks to save or import recipe links, migrate saved Instagram recipes, connect their cookbook, or create a ReelsMeals account. Returns setup links and the agent signup protocol. Public recipe search is free. Private cookbook actions require sign-in, user approval and a paid ReelsMeals plan. Does not create an account or charge anyone by itself.
No parameter schema on file.
Use this when the user asks about their own saved recipes, bookmarked meals or personal cookbook. Search by dish, tags, maker or description. For general recipe discovery use search_public_recipes. Requires a connected account and paid plan.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| limit | integer | no | — |
List the user's recently saved recipes in summary form.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
Use this after searching the user's cookbook to read one of their saved recipes in full by its returned id. Preserve stored ingredients and instructions; cite reelsmealsUrl and the source creator. Use get_public_recipe for an anonymous public result.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Use this when the user asks to import or save a supported recipe URL into their own cookbook. It writes to the cookbook and may enqueue extraction. For an entire saved Instagram collection or many links, use get_reelsmeals_setup for the batch import page instead. Ask before saving.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Replace the user's custom tags for a saved recipe.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| tags | array | yes | — |
Save or replace a user note on a saved recipe.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| note | string | yes | — |
Record that the user cooked a saved recipe, optionally saving a note.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| note | string | no | — |
Choose this week's dinners from the user's saved recipes with optional constraints. Does not persist a plan.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dinners | integer | no | — |
| requireTags | array | no | — |
| excludeTags | array | no | — |
| excludeRecipeIds | array | no | — |
Use this only when the user asks to save a weekly dinner plan from their cookbook. It replaces the saved plan for that week, so confirm replacement first. For dinner ideas without saving use plan_week_from_saved.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| weekOf | string | no | — |
| dinners | integer | no | — |
| requireTags | array | no | — |
| excludeTags | array | no | — |
Aggregate ingredients into a de-duplicated shopping list from explicit recipe ids OR an existing plan id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| recipe_ids | array | no | — |
| plan_id | string | no | — |
Fetch household food preferences, constraints, equipment, and planning notes.
No parameter schema on file.
Update household food preferences, constraints, equipment, and planning notes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dietaryTags | array | no | — |
| dislikedIngredients | array | no | — |
| householdSize | integer | no | — |
| weeknightMaxMinutes | integer | no | — |
| budgetNotes | string | no | — |
| equipment | array | no | — |
| notes | string | no | — |
Fetch recent ReelsMeals MCP tool activity for audit and replay.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
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 ReelsMeals 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 2.1.0 · scanned 20 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 · 2 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest2c0395fb4ea2921ffd161da9857f02789a3f5e1eb1a5ae71eeebdc34c3287fd8
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_public_recipes | no tags | |
| get_public_recipe | no tags | |
| get_reelsmeals_setup | no tags | |
| search_my_cookbook | no tags | |
| list_recent_recipes | no tags | |
| get_recipe | no tags | |
| import_recipe_from_url | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| update_recipe_tags | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| save_recipe_note | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| mark_recipe_cooked | state-write | state-write: declares readOnlyHint: false |
| plan_week_from_saved | no tags | |
| create_weekly_meal_plan | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| build_shopping_list | no tags | |
| get_kitchen_preferences | untrusted-input | untrusted-input: keyword "fetch" |
| update_kitchen_preferences | state-write | state-write: declares readOnlyHint: false |
| get_agent_activity | untrusted-input | untrusted-input: keyword "fetch" |
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 digest2c0395fb4ea2921f
Scanned2026-10-20
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 2.1.0.
2.1.0
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 ReelsMeals 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.