Bryti
REMOTE · API.BRYTI.APP
Plan dinners with Bryti from your own assistant: the week, shopping list, pantry and recipes.
Available components
Last scanned (16 hours ago)
Scores higher than 96% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Productivity and Notes
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security100
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
- The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability81
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 8494 tokens (~143/item across 59 items; 59 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management43
- Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 6 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 60 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 0
- “update_household_settings” added an optional parameter “saveGeneratedRecipes” cosmetic
1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.
- 17 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “save_recipe” rewrote its description, which is the text the model reads security
- Tool “set_household_language” rewrote its description, which is the text the model reads security
- “save_recipe” added an optional parameter “language” cosmetic
- “update_household_settings” added an optional parameter “weekStartsOn” cosmetic
- “adapt_dinner_ingredient” reworded the description of “insteadOfFood” cosmetic
- “adapt_dinner_ingredient” reworded the description of “useFood” cosmetic
- “edit_recipe” reworded the description of “timeline” cosmetic
- “get_shopping_guide” reworded the description of “store” cosmetic
- “save_recipe” reworded the description of “timeline” cosmetic
- “set_category_for_date” reworded the description of “strength” cosmetic
- “set_max_cooking_time_for_date” reworded the description of “strength” cosmetic
- “update_household_settings” reworded the description of “pantryWeight” cosmetic
- “upsert_category_excluded_days_rule” reworded the description of “strength” cosmetic
- “upsert_category_frequency_rule” reworded the description of “strength” cosmetic
- “upsert_category_on_day_rule” reworded the description of “strength” cosmetic
- “upsert_max_cooking_time_rule” reworded the description of “strength” cosmetic
- “upsert_max_total_time_rule” reworded the description of “strength” cosmetic
- “upsert_price_class_rule” reworded the description of “strength” cosmetic
- “upsert_repeat_after_days_rule” reworded the description of “strength” cosmetic
- Tool “set_recipe_favorite” changed its title: Mark a favourite recipe → Mark a favorite recipe cosmetic
- 12 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Nov 26 0
- New tool “set_lunchbox_portions” functional
- “update_household_settings” added an optional parameter “lunchboxWeekdayPortions” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://api.bryti.app/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=bryti.app | CN=YE2,O=Let's Encrypt,C=US | 23 Sept 2026 | 22 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 6fb60fa083019c4eaa4068519b038695194 |
| SANs: *.bryti.app, bryti.app | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of api.bryti.app. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| app. | DS published | 23684 | 8 | Verified |
| bryti.app. | DS published | 2371 | 13 | Verified |
| api.bryti.app. | Verified address RRset verified with the apex keys |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://api.bryti.app/.well-known/oauth-protected-resource/mcp", scope="household:read household:write", error_description="Sign in to Bryti to continue"
Bearer resource_metadata="https://api.bryti.app/.well-known/oauth-protected-resource/mcp", scope="household:read household:write", error_description="Sign in to Bryti to continue" | Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| content-security-policy | frame-ancestors 'none' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | no-referrer |
| permissions-policy | accelerometer=(), camera=(), geolocation=(), gyroscope=(), magnetometer=(), microphone=(), payment=(), usb=() |
Protected resource metadata
| Document | https://api.bryti.app/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://api.bryti.app/mcp |
| Authorisation server | https://api.bryti.app |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.bryti.app/mcp | Verified | 200 | |
| http (plaintext) | http://api.bryti.app/mcp | HTTPS enforced | 301 | https://api.bryti.app/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
update_household_settings Change household settings ~565
Change the household's name, time zone, usual dinner time, address (which decides the stores nearby) or how the week is planned. Only the fields given change. One evening's dinner time is set_dinner_time.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | New address, if changing; empty string clears it. |
| alwaysNewDishes | boolean | – | true makes that number a target instead of a ceiling: exactly that many new dishes every planned week, on the days the cookbook has least to offer. false only invents when the cookbook falls short. |
| defaultDinnerTime | string | – | New default dinner time as HH:mm, if changing. |
| lunchboxWeekdayPortions | integer | – | 0–6: how many extra portions the dinner the night before a weekday cooks for tomorrow's lunchboxes. 0 = none. One dinner's own number is set on its day card. |
| maxNewDishesPerWeek | integer | – | 0–7: how many of the week's dinners Bryti may invent. The rest are taken from the household's own recipes and the built-in library. 0 = only dishes they already know. |
| name | string | – | New household name, if changing. |
| pantryWeight | string | – | How much the week leans on what the household already has at home. Usual: what they like and their favourites go first, the pantry breaks ties. Prefer («bruk gjerne det vi har» / «use what we have»):… |
| prefersLeftoverDinners | boolean | – | true plans a leftovers evening roughly every third day, eating what the two days before cooked; false plans cooking every day. |
| saveGeneratedRecipes | boolean | – | true puts every dish Bryti makes up straight into the cookbook. false (the default) leaves a new dish on its day only; the household saves the ones they want, and an unsaved one is never suggested ag… |
| timeZoneId | string | – | IANA time zone id, e.g. 'Europe/Oslo', if changing. Only when the user says where they are or asks to change the zone — never guessed from the language they write in. |
| weekStartsOn | string | – | The day the household's calendar starts on: Monday, or Sunday (common in the US). Sunday also names each week by its dates instead of its week number. Plans still run Monday to Sunday either way. |
No output schema declared.
No examples provided.
upsert_category_excluded_days_rule Keep a category off some days ~229
Set the weekdays a meal category is never planned. A rule about the same thing is changed, not added twice. Soft unless the household says it must hold.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | yes | The meal category. |
| excludedWeekdays | array | yes | Weekdays to exclude. |
| strength | string | yes | Soft unless the household says the rule must hold. Hard ONLY when the words are must/never/always (må/aldri/alltid/skal/kan ikke/ikke lov). Everything else is Soft — a preference the planner may bend… |
No output schema declared.
No examples provided.
upsert_category_frequency_rule Set how often a category comes ~251
Set how many times a week a meal category should be on the plan, at least and at most. A rule about the same thing is changed, not added twice. Soft unless the household says it must hold.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | yes | The meal category. |
| maximumPerWeek | integer | yes | Maximum dinners per week. |
| minimumPerWeek | integer | yes | Minimum dinners per week. |
| strength | string | yes | Soft unless the household says the rule must hold. Hard ONLY when the words are must/never/always (må/aldri/alltid/skal/kan ikke/ikke lov). Everything else is Soft — a preference the planner may bend… |
No output schema declared.
No examples provided.
upsert_category_on_day_rule Put a category on a weekday ~249
Set that a meal category belongs on a weekday every week, e.g. taco on Fridays. One single date is set_category_for_date. A rule about the same thing is changed, not added twice. Soft unless the household says it must hold.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | yes | The meal category. |
| strength | string | yes | Soft unless the household says the rule must hold. Hard ONLY when the words are must/never/always (må/aldri/alltid/skal/kan ikke/ikke lov). Everything else is Soft — a preference the planner may bend… |
| weekday | string | yes | The weekday it belongs on, week after week. |
No output schema declared.
No examples provided.
upsert_max_cooking_time_rule Limit time at the stove ~284
Set the most minutes of active cooking a dinner may take, every day or on the weekdays named. One single date is set_max_cooking_time_for_date; the time until dinner is on the table, oven included, is upsert_max_total_time_rule. A rule about the same thing is changed, not added twice. Soft unless the household says it must hold.
| Name | Type | Req | Description |
|---|---|---|---|
| minutes | integer | yes | Maximum active minutes at the stove, 5-240. |
| strength | string | yes | Soft unless the household says the rule must hold. Hard ONLY when the words are must/never/always (må/aldri/alltid/skal/kan ikke/ikke lov). Everything else is Soft — a preference the planner may bend… |
| weekdays | array | – | The weekdays the maximum holds on; omit for every day. |
No output schema declared.
No examples provided.
upsert_max_total_time_rule Limit time until dinner ~262
Set the most minutes from the first step until dinner is on the table, oven and resting included, every day or on the weekdays named. A rule about the same thing is changed, not added twice. Soft unless the household says it must hold.
| Name | Type | Req | Description |
|---|---|---|---|
| minutes | integer | yes | Maximum minutes from the first step to the table, 10-240. |
| strength | string | yes | Soft unless the household says the rule must hold. Hard ONLY when the words are must/never/always (må/aldri/alltid/skal/kan ikke/ikke lov). Everything else is Soft — a preference the planner may bend… |
| weekdays | array | – | The weekdays the maximum holds on; omit for every day. |
No output schema declared.
No examples provided.
upsert_price_class_rule Keep dinners cheap ~269
Set how dear dinners may be, every day or on the weekdays named: Cheap, or CheapOrMid. Bryti prices each dinner from store prices; there is no amount in kroner. A rule about the same thing is changed, not added twice. Soft unless the household says it must hold.
| Name | Type | Req | Description |
|---|---|---|---|
| ceiling | string | yes | The dearest class allowed: Cheap, or CheapOrMid. |
| strength | string | yes | Soft unless the household says the rule must hold. Hard ONLY when the words are must/never/always (må/aldri/alltid/skal/kan ikke/ikke lov). Everything else is Soft — a preference the planner may bend… |
| weekdays | array | – | The weekdays the rule holds on; omit for every day. |
No output schema declared.
No examples provided.
upsert_repeat_after_days_rule Space out the same dish ~242
Set how many days must pass before the same dish comes back, 3 to 30. Bryti's default is 10. A rule about the same thing is changed, not added twice. Soft unless the household says it must hold.
| Name | Type | Req | Description |
|---|---|---|---|
| days | integer | yes | Days between two servings of the same dish, 3–30. |
| strength | string | yes | Soft unless the household says the rule must hold. Hard ONLY when the words are must/never/always (må/aldri/alltid/skal/kan ikke/ikke lov). Everything else is Soft — a preference the planner may bend… |
No output schema declared.
No examples provided.
wish_dish Wish for a dish ~131
Put a dish on the household's wish list, or add a vote when it is already there. A wish lifts the dish in the next planned week; it is a weight, never a rule. A title from get_recipes gives that recipe; any other name is kept as said.
| Name | Type | Req | Description |
|---|---|---|---|
| memberName | string | – | The member the wish is for when someone wishes on a child's behalf; omit for the speaker's own wish. |
| title | string | yes | The dish: its exact cookbook title when it is in the cookbook, else the user's own words, e.g. 'pannekaker'. |
No output schema declared.
No examples provided.
How do I install the Bryti MCP server?
Bryti is a hosted endpoint at https://api.bryti.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.bryti.app
claude mcp add --transport http app-bryti-bryti 'https://api.bryti.app/mcp'
What is the Bryti MCP server?
Bryti is an MCP server listed in the public MCP registry as app.bryti/bryti. Plan dinners with Bryti from your own assistant: the week, shopping list, pantry and recipes. This page covers its hosted endpoint (https://api.bryti.app/mcp).
Is the Bryti MCP server safe to use?
Bryti scores 89 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Bryti MCP server expose?
Bryti exposes 59 tools: get_household_overview, get_rules, get_week_plan, get_inventory, get_shopping_list, and 54 more. Their descriptions and schemas cost roughly 8,117 tokens of context every time the server is loaded.
Does the Bryti MCP server require authentication?
Yes. Bryti asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Bryti MCP server still maintained?
Bryti is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Bryti MCP server?
VerifyMCP ran 13 checks on Bryti, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.