MCP servers › how.mise › mise
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
how.mise/mise
Ad-free recipes with amounts in every step: search, scale, plan meals, build shopping lists. — the publisher's description
Summary
how.mise/mise is a remote MCP server listed in the official MCP registry at version 0.1.0, marked deprecated there. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 25 tools, 1 resource and 5 prompts.
Record checks
0 of 2 record checks met · 7 do not apply
- not met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: deprecated in the registry
- Not ranked by stars: deprecated in the registry
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Sign-in
- none needed to open a session
- Tools
- 25
- Described as changing data
- 18 of 25 toolsAI-classified
- Mainly works on
- files and code on the machine it runs onAI-classified
- Topic
- otherAI-classified
- Last tested
- 2026-10-23
Observed fact
This server accepted a session without any credential and lists 7 tools whose name or declaration suggests they change data (update_shopping_list, update_meal_plan, create_recipe, update_recipe, delete_recipe and 2 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.
Worth knowing before you connect it
- 18 tools are described as changing something (build_shopping_list, update_shopping_list, plan_meals, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.
- The registry marks this server deprecated.
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 0.1.0, published 2026-10-11 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-11 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-22
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.1.0 (published 2026-10-11).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventoryWhat it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on.
18 of 25 tools are described as changing something (creating, editing, deleting, sending or running).
“Find recipes on Befana by keywords, ingredients, time or diet.”
Publisher declares: read-only yes · open-world no
12 inputs
allergensarray“Explicit per-request allergen screening, separate from exclude_ingredients.”unknown_ingredientsstring“While allergen screening is active: exclude (default) omits insufficiently classified recipes; flag includes them with uncertainty.”querystring“Keywords, e.g.”mineboolean“Only the cook's own recipes and versions, including private ones”max_minutesinteger“Maximum prep + cook time as the author wrote it (total_minutes).”max_caloriesinteger“Calories per serving at most ("under 500 calories").”min_proteininteger“Grams of protein per serving at least ("high protein": 30).”tagsarray“All must match.”include_ingredientsarray“Ingredients the recipe must use, e.g.”exclude_ingredientsarray“Ingredient-name/canonical exclusions only, NOT allergen rules.”from_pantryboolean“Rank by what the cook has in their saved pantry ("something with pasta from what I have"); each result says what they have and what's missing.”limitinteger
“One recipe in full, scaled to any servings, US or metric, with every amount written into the step that uses it, so steps can be read aloud as they are.”
Publisher declares: read-only yes · open-world no
7 inputs, 1 required
allergensarray“Explicit per-request allergen screening, separate from exclude_ingredients.”unknown_ingredientsstring“While allergen screening is active: exclude (default) omits insufficiently classified recipes; flag includes them with uncertainty.”slugstringrequired“Recipe slug from search_recipes”servingsnumber“Scale to this many servings (defaults to the cook's household size, then the recipe's own)”unitsstring“US cups/oz/°F or metric grams/ml/°C.”units_forobject“The cook's own unit for particular ingredients, by ingredient key or name: { "butter": "tbsp", "flour": "g" }.”substituteobject“Ask for substitutions: for one ingredient, for a diet, or both”
“A recipe as hands-free steps for cooking along: a gather list, then one step at a time with its amounts, the ingredients it uses, its tip and any timer.”
Publisher declares: read-only yes · open-world no
8 inputs, 1 required
allergensarray“Explicit per-request allergen screening, separate from exclude_ingredients.”unknown_ingredientsstring“While allergen screening is active: exclude (default) omits insufficiently classified recipes; flag includes them with uncertainty.”slugstringrequiredservingsnumberunitsstring“US cups/oz/°F or metric grams/ml/°C.”units_forobject“The cook's own unit for particular ingredients, by ingredient key or name: { "butter": "tbsp", "flour": "g" }.”stepinteger“Just this step (1-based), for "what's next?" in a voice flow; the gather list comes only with step 1 or no step”from_stepinteger“This step and the rest, e.g.”
“Merge recipes (each at its own servings) and anything else into one shopping list by aisle, in what a store sells (10 cloves garlic → 1 head).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
8 inputs, 1 required
recipesarrayrequiredpantryarray“Ingredients the cook already has, e.g.”include_staplesboolean“Put salt, oil, sugar, etc.”extra_itemsarray“Anything else for the same trip, as the cook said it, amount included: ["paper towels", "2 lb bananas"].”unitsstring“US cups/oz/°F or metric grams/ml/°C.”savestring“"preview": show the list and keep nothing (no id, no url, nothing in My Kitchen), signed in or out; use it when the cook says "just show me", "don't save it ye…”request_keystring“Your own id or receipt.request_key.”keepboolean“Older spelling of save: true = save, false = preview.”
“Change a saved list after the cook answers what build_shopping_list or plan_meals set aside as likely_have, or says how the trip went.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 1 required
list_idstringrequired“Id of the saved list from build_shopping_list or plan_meals”removearray“Things the cook has, as they said them: ["flour", "olive oil"]”needarray“Set-aside (likely_have) things the cook is out of: they go back to the buy list at full size”addarray“Anything else for the same trip, amount included: ["paper towels", "2 lb bananas"]”outcomesarray“How the trip went, per line (#63): what they bought, skipped, or got somewhere else”
“Plan dinners and return the finished week in one call: picks by day (varied, perishables first, one new to the cook), merged shopping list (list), prep_order, substitutions and one true line (say).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
17 inputs
mealsinteger“How many meals to plan; leave out to use the cook's usual number (workflow.plan_meals in preferences), else 5”servingsnumber“Servings per meal (defaults to each recipe's own)”tagsarray“Required tags, e.g.”meal_typestringoccasionstring“weeknight: quick, everyday.”guest_notesstring“Who's coming and what they need, in the cook's words: "one vegetarian, Sam hates cilantro".”max_minutesintegermax_caloriesinteger“Calories per serving at most for every meal; defaults to the cook's saved target”min_proteininteger“Grams of protein per serving at least; defaults to the cook's saved target”max_budgetnumber“US dollars the plan's list should stay under ("plan the week under $80"): an estimate from national average prices, so say "about"”exclude_ingredientsarraywith_shopping_listbooleanpantryarrayunitsstring“US cups/oz/°F or metric grams/ml/°C.”savestring“"preview": show the plan and keep nothing (no id, no url, nothing in My Kitchen), signed in or out; use it when the cook says "just show me", "don't save it ye…”request_keystring“Your own id or receipt.request_key.”keepboolean“Older spelling of save: true = save, false = preview.”
“Change the cook's saved meal plan in place: swap a day for another pick (constraints: faster, max_minutes, tags, query, or a slug the cook chose), drop a day, or add one, keeping their other days.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 1 required
plan_idstringrequired“plan_id from plan_meals”swaparray“Days to change: [{ day: "Tue", constraints: { faster: true } }]”droparray“Days to take out of the plan: ["Thu"]”addarray“Meals to add: [{}] for one more dinner”with_shopping_listboolean“Rebuild the plan's list in place (the default)”pantryarrayunitsstring“US cups/oz/°F or metric grams/ml/°C.”
“Send a shopping list to a grocer near the cook: into their cart where the store allows it (King Soopers and other Kroger stores, once connected), else one list link, else a search link per item.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
12 inputs
list_idstring“Id of a saved list from build_shopping_list or plan_meals”recipesarraypantryarray“Ingredients the cook already has; they are not ordered”unitsstring“US cups/oz/°F or metric grams/ml/°C.”providerstring“Grocer to hand the list to: instacart, walmart, kroger, amazon or search.”storestring“The store the cook picked or named ("Sprouts", "King Soopers"), ideally one from choose_store.”zipstring“The cook's ZIP code, when they gave it; saved with their store.”remember_storeboolean“false for a one-off order elsewhere; the saved store stays as it was”previewboolean“A cart grocer previews before adding anything (the default).”preview_idstring“A cart_preview's id: with edits it updates the preview, with confirm: true it adds exactly those items to the cart”confirmboolean“true, with preview_id, once the cook said yes to the preview”editsarray“The cook's changes to a preview ("skip the hoisin", "2 salmon"), with preview_id”
“Turn a recipe the cook pasted, typed or linked into a draft to check: ingredients matched, steps in plain words with the amounts as tags, servings, times and timers filled in.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs
textstring“The recipe as the cook gave it, in any format”urlstring“A public recipe page (http or https), or a Pinterest Pin or pin.it link (Befana follows the Pin to the recipe it saved).”source_urlstring“With text: the web page the recipe text came from, to credit it and to find it if it's already on Befana”add_anywayboolean“Draft it even though it matched a recipe already on Befana (only when the cook says it's a different recipe)”
“Publish a recipe to Befana.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
14 inputs
draft_idstring“A draft_id from draft_recipe, to publish that draft”titlestringsummarystring“One or two sentences on what makes it good”servingsnumberyield_labelstring“servings, cookies, loaves, jars…”prep_minutesintegercook_minutesintegertagsarrayauthorstring“Name to credit (the cook)”chef_notestring“The chef's note, up to 500 characters: a sentence or two in the cook's words on what makes the recipe theirs.”ingredientsarraystepsarraytestedobject or null“Mark the recipe tested: the cook says they cooked it themselves and timed it.”visibilitystring“private = just for the cook, from the first save (#171); public (the default) lists it under My recipes and in search”
“Draw a labeled illustration of the dish for a recipe the cook owns that has no photo, so it looks finished until they add a real one.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
1 input, 1 required
slugstringrequired“The cook's own recipe”
“Save the cook's own version of someone else's recipe, linked to the original, which never changes.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
13 inputs, 1 required
slugstringrequired“The original recipe's slug”visibilitystring“private = just for the cook; public (the default) lists it under the original”titlestringsummarystring“One or two sentences on what makes it good”servingsnumberyield_labelstring“servings, cookies, loaves, jars…”prep_minutesintegercook_minutesintegertagsarrayauthorstring“Name to credit (the cook)”chef_notestring“The chef's note, up to 500 characters: a sentence or two in the cook's words on what makes the recipe theirs.”ingredientsarraystepsarray
Show 13 more tools
“Change the cook's own recipe or version.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
20 inputs, 1 required
slugstringrequired“The cook's recipe or version to change”recover_photoobject“Recover an uploaded cover without another intake.”restore_revisioninteger“Undo: put the recipe back to how it was before edit n (see get_recipe's revisions).”visibilitystringshow_countsboolean“Whether the page shows "cooked N times · shared N times" once there are enough cooks (#46); default on.”unpublishedboolean“true takes the recipe off Befana for everyone but the cook (the link stays theirs, nothing is lost, their lists and plans still open it); false puts it back.”photoobject“A photo the cook took of this dish: the cover, or a step with step.”attached_photoobject“A JPG, PNG or WebP photo the cook attached in the chat, for the cover (or a step with photo.step).”titlestringsummarystring“One or two sentences on what makes it good”servingsnumberyield_labelstring“servings, cookies, loaves, jars…”prep_minutesintegercook_minutesintegertagsarrayauthorstring“Name to credit (the cook)”chef_notestring“The chef's note, up to 500 characters: a sentence or two in the cook's words on what makes the recipe theirs.”ingredientsarraystepsarraytestedobject or null“Mark the recipe tested: the cook says they cooked it themselves and timed it.”
“Delete a recipe the cook owns, for good, when nobody else has touched it (no versions, reviews or saves by other cooks).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 1 required
slugstringrequired“The cook's own recipe”confirmboolean“true only after the cook said yes to deleting this recipe by name”
“Read only the signed-in cook's saved private feedback and the recipe-as-written context (US units, original servings).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
slugstringrequired
“Post the cook's star rating (1 to 5) and comment, and mark that they made it.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
10 inputs, 2 required
step_feedbackarray or nullsubstitutions_madearray or nullwould_make_againstring or nullcontent_tokenstringslugstringrequiredstarsintegerrequiredcommentstringcook_session_idstring“Session returned by get_cook_steps; identifies the cook being completed, validated against the signed-in cook and recipe.”made_itboolean“Set true only when the cook explicitly says they made it; omission preserves the review and does not finish a cook.”namestring“Display name the cook wants shown (defaults to their account name)”
“Keep a recipe in the cook's Saved list (My Kitchen on the website), or take it off with saved: false.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 1 required
slugstringrequired“Recipe slug from search_recipes”savedboolean“false takes it off Saved (only when the cook asks)”
“What the cook keeps on Befana: saved recipes, recipes they published, their own versions, shopping lists and meal plans, their ratings, a pantry count.”
Publisher declares: read-only yes · open-world no
5 inputs
sectionstring“photos: recipes needing a better cover.”target_recipestring“Required only with pending_photos: the exact recipe slug whose cover the cook wants to recover”pending_cursorstring“Only with pending_photos: next_cursor from the preceding page”expected_actorstring“For later pending_photos pages, copy expected_actor from discovery; an account consistency check, never authorization”limitinteger“Items per ordinary kitchen section; pending_photos always returns at most 30”
“Hand back a recipe the Befana team added to the cook's kitchen (get_my_kitchen newly_assigned) when the cook says "that one isn't mine".”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
slugstringrequired
“How the cook's own recipes are doing: views, shares, prints, cooks, saves, versions and ratings, in total and by day, per recipe and by region.”
Publisher declares: read-only yes · open-world no
2 inputs
rangestring“The window; all is all-time totals with a year of daily rows”recipestring“One of the cook's recipes, by slug, for just that recipe”
“Read or change the cook's pantry: food on hand and staples, which Befana leaves off shopping lists and uses for what-can-I-make.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
6 inputs
textstring“What the cook said, verbatim”photostring“An upload name (or its /media/ URL) from POST /api/upload with purpose "parse": a photo of the fridge or shelf to read”addarray“Ingredient names to add”removearray“Ingredient names to take out”replaceboolean“Take out every fresh item not in this update (staples stay)”staplesarray“Set the always-on-hand list to exactly these”
“Recipes ranked by how much the cook already has, each with what's missing ("You have 7 of 9.”
Publisher declares: read-only yes · open-world no
6 inputs
pantryarray“Ingredient names to use instead of the saved pantry (signed out, or a what-if)”must_usearray“Ingredients the recipe has to use”querystring“Keywords, e.g.”tagsarraymax_minutesintegerlimitinteger
“Read or change the cook's Befana preferences: allergies, diet, avoid list, household size, units, weeknight time, skill, equipment, cuisines, store, privacy, and how they want you to work, all applie…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
20 inputs
cook_confirmedboolean“Required to change anything: true only when the cook asked for this exact change in their own words (non-health settings) or said yes after you restated it (al…”allergiesarray“Major allergens: milk, eggs, fish, shellfish, tree_nuts, peanuts, wheat, soy, sesame”custom_allergiesarray“Other allergy ingredients, e.g.”dietsarrayavoidarray“Ingredients the cook dislikes”avoid_modestring“exclude hides those recipes; rank_lower shows them lower”servingsinteger or null“Household size; null to use each recipe's own”servings_modestring“offer (default): recipes open at their own servings and the household size is offered; always: recipes open scaled to it.”unitsstringweeknight_minutesinteger or nullskillstring or nullequipmentarraycuisines_lovearraycuisines_skiparraypantryarray“Always-on-hand staples”storeobjectdo_not_sellboolean“True keeps the cook out of every aggregated data product Befana sells or licenses”share_regionboolean“False stops usage counts from recording the cook's state or country”nutrition_targetsobject“Targets for one serving that plan_meals and search_recipes use by default ("keep dinners under 600 calories").”workflowobject“How the cook wants you to work with them.”
“Read a cook's public Befana page, or change the signed-in cook's own.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
3 inputs
handlestring“Whose page to read, e.g.”updateobject“Changes to the signed-in cook's own profile; interests and links replace the saved lists.”cook_confirmedboolean“Required with update: true only after the cook said yes to this exact change”
“Flag a recipe, review, photo or a cook's profile for Befana's moderators: spam, offensive, unsafe as written, copied without permission, not a recipe, or something else.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 3 required
kindstringrequiredidstringrequired“The recipe slug, the review id, the photo URL, or the cook's handle for a profile”reasonstringrequired“spam: Spam or advertising; offensive: Offensive or hateful; unsafe: Unsafe to cook or eat as written; copyright: Copied without permission; not_recipe: Not a r…”notestring“What's wrong, in the cook's words”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
- Says what the tool does
- 100% of 25 tools
- Says what it returns
- 59% of 22 tools
- States limits, defaults or errors
- 22% of 23 tools
- Says when to use it
- 100% of 25 tools
- Items covered per tool
- 2.9 of 4 on average
Counted from the listing
- Parameters with a description
- 72% of 190
- Tools with a description
- 100% of 25
- Typical description length
- 629 characters
The tool set
Counted from the listing
- Tools
- 25
- Size of the list
- about 76,172 tokens for an agent to load (characters ÷ 4)
- Naming
- 23 of 25 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 25 of 25 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-10-23 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://mise.how/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"mise": {
"url": "https://mise.how/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"mise": {
"type": "http",
"url": "https://mise.how/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"mise","type":"http","url":"https://mise.how/mcp"}'Claude Code
claude mcp add --transport http mise https://mise.how/mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://mise.how/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint mise.how/mcp | Session opened | matches | our test · 2026-10-23 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-23 |
Same tools as other registry entries
Tool lists read · names comparedIts 25 tools have exactly the same names as the tools of 1 other registry entry (published under 2 registry namespaces). Their tool descriptions are also word for word the same.
This can be one publisher's family of servers or one template reused under many names. It is a fact about the published tool lists, not a judgement of the publisher and not a safety finding; we compared tool names, not code.
Shared tool names (12 of 25 shown):
build_shopping_listcook_profilecreate_recipedelete_recipedraft_recipefork_recipegenerate_placeholder_coverget_cook_stepsget_my_kitchenget_my_recipe_feedbackget_my_statsget_recipeThe other entries
All groups of servers with identical tool lists
Source: our read-only reads of each server's tool list · 2026-10-23. No tool was called.
Choosing
Record checks
Public records · not a safety rating0 of 2 record checks met · 7 do not apply
- Not ranked by downloads: deprecated in the registry
- Not ranked by stars: deprecated in the registry
- Not metRegistry entry is active and says how to run itThe registry marks this entry as deprecated.
- Not metSource repository link opensThe registry entry gives no repository link.
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards
Common questions about how.mise/mise
Answered from the data aboveIs how.mise/mise safe to install?
We do not rate servers as safe or unsafe. 0 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its registry entry is marked deprecated. 18 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Does how.mise/mise need an API key or sign-in?
It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.
Has how.mise/mise been security tested?
Partly. 5 of the 16 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.
What can how.mise/mise do?
It lists 25 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete and generate content. We did not call any tool, so this describes the text, not the behaviour.
Can how.mise/mise change or delete data?
18 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Similar servers
Same topic · AI-read
- com.aisenseapi/free-public-toolsAI SENSE Free Public Toolsalso has tools that creates or changes data, deletes, generates content, reads or searchescompare with this one
- io.github.pipeworx-io/19hz19hzalso has tools that creates or changes data, deletes, generates content, reads or searchescompare with this one
- io.github.pipeworx-io/adviceAdvicealso has tools that creates or changes data, deletes, generates content, reads or searchescompare with this one
- io.github.pipeworx-io/ai-feedsAi Feedsalso has tools that creates or changes data, deletes, generates content, reads or searchescompare with this one
- io.github.pipeworx-io/always-sevenAlways Sevenalso has tools that creates or changes data, deletes, generates content, reads or searchescompare with this one
- io.github.pipeworx-io/amplitudeAmplitudealso has tools that creates or changes data, deletes, generates content, reads or searchescompare with this one
Active servers whose topic is also “other” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: exercised
- Fake assistant turns: exercised
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
5 exercised11 not run (reason given)2 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 5 of the 16 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised - 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 2,081 msConnected after 1 redirect. No credential was sent or needed.
- Read the inventory: 25 tools, 1 resource, 5 prompts.
- 7,881 msFinished: 5 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “how.mise/mise: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/how.mise/mise
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/how.mise/mise)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology