Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Fatsecret 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.
97/100
trust score
21
downloads a day
local
runs on your machine
352
downloads in 30d
What it does
MCP server for FatSecret API - food search, nutrition, diary, recipes, weight tracking (unofficial)
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'FATSECRET_CLIENT_ID=${FATSECRET_CLIENT_ID}' --env 'FATSECRET_CLIENT_SECRET=${FATSECRET_CLIENT_SECRET}' --env 'FATSECRET_CONSUMER_SECRET=${FATSECRET_CONSUMER_SECRET}' --transport stdio fatsecret-mcp '--' npx -y fatsecret-mcp
# 2 — ask your agent for something these tools do
# search_foods, get_food, find_food_by_barcode and 41 more
It needs FATSECRET_CLIENT_ID, FATSECRET_CLIENT_SECRET, FATSECRET_CONSUMER_SECRET: this reads them from your environment, so export them first.
Fatsecret costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
FLAll 2 servers
fliptheweb2 servers
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Fatsecret as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads FATSECRET_CLIENT_ID (FatSecret API Client ID), FATSECRET_CLIENT_SECRET (FatSecret API Client Secret (OAuth 2.0)), FATSECRET_CONSUMER_SECRET (FatSecret API Consumer Secret (OAuth 1.0)) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx FATSECRET_CLIENT_ID …, setx FATSECRET_CLIENT_SECRET …, setx FATSECRET_CONSUMER_SECRET … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'FATSECRET_CLIENT_ID=${FATSECRET_CLIENT_ID}' --env 'FATSECRET_CLIENT_SECRET=${FATSECRET_CLIENT_SECRET}' --env 'FATSECRET_CONSUMER_SECRET=${FATSECRET_CONSUMER_SECRET}' --transport stdio fatsecret-mcp '--' npx -y fatsecret-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: FATSECRET_CLIENT_ID — FatSecret API Client ID; FATSECRET_CLIENT_SECRET — FatSecret API Client Secret (OAuth 2.0); FATSECRET_CONSUMER_SECRET — FatSecret API Consumer Secret (OAuth 1.0). You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
44 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 the FatSecret food database. Returns food names, descriptions, and basic nutrition info.
No parameter schema on file.
Get detailed nutritional information for a specific food by ID. Returns servings, calories, macros, and micronutrients.
No parameter schema on file.
Find food by barcode (GTIN-13). UPC-A, EAN-13 and EAN-8 supported. Premier exclusive.
No parameter schema on file.
Get autocomplete suggestions for a partial food search expression. Premier exclusive.
No parameter schema on file.
Search recipes with optional filters for calories, macros, prep time, and recipe types.
No parameter schema on file.
Get detailed recipe information by ID including ingredients, directions, and nutrition.
No parameter schema on file.
Get the full list of food categories. Premier exclusive.
No parameter schema on file.
Get food sub categories for a given food category. Premier exclusive.
No parameter schema on file.
Get the list of food brands, optionally filtered by starting letter and type. Premier exclusive.
No parameter schema on file.
Get the full list of supported recipe type names.
No parameter schema on file.
Get food diary entries for a date or a specific entry by ID. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get daily nutrition summary for a month. Returns calories and macros per day. Requires profile auth (check_auth_status first).
No parameter schema on file.
Add a food diary entry. Requires food_id, serving_id, and meal type. Requires profile auth (check_auth_status first).
No parameter schema on file.
Edit an existing food diary entry. Cannot change the date. Requires profile auth (check_auth_status first).
No parameter schema on file.
Delete a food diary entry by ID. Requires profile auth (check_auth_status first).
No parameter schema on file.
Copy food entries from one date to another, optionally filtered by meal. Requires profile auth (check_auth_status first).
No parameter schema on file.
Copy entries from a saved meal to a meal on a specific date. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get the user's favorite foods. Requires profile auth (check_auth_status first).
No parameter schema on file.
Remove a food from the user's favorites. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get the user's most eaten foods, optionally filtered by meal. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get the user's recently eaten foods, optionally filtered by meal. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get the user's favorite recipes. Requires profile auth (check_auth_status first).
No parameter schema on file.
Add a recipe to the user's favorites. Requires profile auth (check_auth_status first).
No parameter schema on file.
Remove a recipe from the user's favorites. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get the user's saved meals, optionally filtered by meal type. Requires profile auth (check_auth_status first).
No parameter schema on file.
Create a new saved meal. Requires profile auth (check_auth_status first).
No parameter schema on file.
Edit a saved meal name, description, or associated meals. Requires profile auth (check_auth_status first).
No parameter schema on file.
Delete a saved meal. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get all food items in a saved meal. Requires profile auth (check_auth_status first).
No parameter schema on file.
Add a food item to a saved meal. Requires profile auth (check_auth_status first).
No parameter schema on file.
Edit a food item in a saved meal (name or units). Cannot change serving_id. Requires profile auth (check_auth_status first).
No parameter schema on file.
Remove a food item from a saved meal. Requires profile auth (check_auth_status first).
No parameter schema on file.
Record the user's weight for a date. First weigh-in requires goal_weight_kg and current_height_cm. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get the user's weight entries for a month. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get the full list of supported exercise types and their IDs. Requires profile auth (check_auth_status first).
No parameter schema on file.
Shift exercise time between activities for a date. Moves minutes from one exercise to another. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get daily calories expended from exercise for a month. Requires profile auth (check_auth_status first).
No parameter schema on file.
Save the current day's exercise entries as a template for specified days of the week. Requires profile auth (check_auth_status first).
No parameter schema on file.
Get profile status information for the authenticated user. Requires profile auth (check_auth_status first).
No parameter schema on file.
Create a custom food with nutrition info. Premier exclusive. Requires profile auth (check_auth_status first).
No parameter schema on file.
Check if API credentials and profile authentication are configured. Call this first to understand what setup is needed.
No parameter schema on file.
Configure FatSecret API credentials. Get them at https://platform.fatsecret.com/ → My Account → API Keys. Saves to persistent config file.
No parameter schema on file.
Start the OAuth 1.0 authorization flow for profile access. Returns an authorization URL the user must visit. Requires API credentials (setup_credentials first).
No parameter schema on file.
Complete the OAuth 1.0 flow with the verifier code from the authorization page.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- 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 Fatsecret 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: —
ATrust score 97 / 100
Release 0.0.9 · scanned 14 Oct 2026
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 score97
Findings1 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest09e615173045672e05df5fa529ee9fcf13a095754bc4cb88d340f39918060ce1
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (44 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
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_foods | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_food | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| find_food_by_barcode | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| autocomplete_foods | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_recipes | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_recipe | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_food_categories | no tags | |
| get_food_sub_categories | no tags | |
| get_brands | no tags | |
| get_recipe_types | no tags | |
| get_food_entries | no tags | |
| get_food_entries_month | no tags | |
| create_food_entry | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/food-entries/v1') at dist/index.js:327 |
| edit_food_entry | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( this.profileClient.PUT('/food-entries/v1') at dist/index.js:337 |
| delete_food_entry | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| copy_food_entries | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/food-entries/copy/v1') at dist/index.js:357 |
| copy_saved_meal_entries | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/food-entries/copy/saved-meal/v1') at dist/index.js:374 |
| get_favorite_foods | no tags | |
| delete_favorite_food | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/food/favorite/v1') at dist/index.js:397 |
| get_most_eaten_foods | no tags | |
| get_recently_eaten_foods | no tags | |
| get_favorite_recipes | no tags | |
| add_favorite_recipe | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/recipe/favorites/v1') at dist/index.js:437 |
| delete_favorite_recipe | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| get_saved_meals | no tags | |
| create_saved_meal | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/saved-meals/v1') at dist/index.js:470 |
| edit_saved_meal | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( this.profileClient.PUT('/saved-meals/v1') at dist/index.js:480 |
| delete_saved_meal | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| get_saved_meal_items | no tags | |
| add_saved_meal_item | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/saved-meals/item/v1') at dist/index.js:510 |
| edit_saved_meal_item | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( this.profileClient.PUT('/saved-meals/item/v1') at dist/index.js:520 |
| delete_saved_meal_item | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| update_weight | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/weight/v1') at dist/index.js:543 |
| get_weight_month | no tags | |
| get_exercises | no tags | |
| edit_exercise_entries | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP PUT ( this.profileClient.PUT('/exercise-entries/v1') at dist/index.js:576 |
| get_exercise_entries_month | no tags | |
| save_exercise_template | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/exercise-entries/day/v1') at dist/index.js:596 |
| get_profile | no tags | |
| create_food | state-writeexternal-sink | state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( this.profileClient.POST('/food/v2') at dist/index.js:619 |
| check_auth_status | no tags | |
| setup_credentials | state-write | state-write: declares readOnlyHint: false |
| start_auth | no tags | |
| complete_auth | state-write | state-write: declares readOnlyHint: false |
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 digest09e615173045672e
Scanned2026-10-14
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.0.9. Pin a release below and the command asks for exactly that one.
0.0.9
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 Fatsecret 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.