MCP servers › io.github.cook-md › cook-mcp
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.cook-md/cook-mcp
Cooklang recipes for AI agents: validate, meal plans, shopping lists, pantry, nutrition — the publisher's description
Summary
io.github.cook-md/cook-mcp is a local MCP server listed in the official MCP registry at version 0.2.3. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 24 tools, 17 resources and 8 prompts.
Record checks
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- not met: Repository publishes a security policy (SECURITY.md)
- met: Package names its licence with a standard (SPDX) identifier
- met: The version the registry lists can be installed and is not withdrawn
- met: npm package carries build provenance (attestation)
- met: No known critical or high advisory in the package or its dependencies
- #6,929 of 15,112 packages by monthly downloads, tied with 15 others
- Not ranked by stars: 2 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- local package
- Transport
- standard input/output
- Package
- npm · listed version current
- License
- MIT
- Dependencies
- no known high or critical advisories
- Repository
- public
- Tools
- 24
- Described as changing data
- 7 of 24 toolsAI-classified
- Mainly works on
- files and code on the machine it runs onAI-classified
- Pricing
- freemiumAI-classified
- Last tested
- 2026-10-23
Worth knowing before you connect it
- 7 tools are described as changing something (import_recipe, login, pantry_update, …): our AI model's reading of the descriptions, not something we tested. We did not call them.
- Its package is signed and carries a build record naming its source.
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
- 0.2.3, published 2026-10-06 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-06 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- 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 0.2.3 (published 2026-10-06).
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.
7 of 24 tools are described as changing something (creating, editing, deleting, sending or running).
- aggregate_nutritioncalculates or converts
“Sum nutrition across many ingredient lines (a whole recipe).”
4 inputs, 1 required
exclusionsarray or null“Ingredient names/categories that must be absent; matches come back in the response's exclusion fields.”itemsarrayrequired“Ingredient lines to sum.”referencestring or nullregionstring or null“Default region for cup/tbsp/tsp sizing, applied to items that don't set their own: "us" (default), "uk", or "metric".”
“Report login status, Cook plan and import allowance.”
Takes no inputs.
- branded_lookupreads or searches
“Look up a branded/packaged product by UPC barcode or text search.”
2 inputs
qstring or null“Brand or product text search.”upcstring or null“GTIN/UPC barcode for an exact match.”
- check_categoryreads or searches
“Check whether an ingredient belongs to a category slug.”
2 inputs, 2 required
ingredientstringrequiredslugstringrequired“Category slug, e.g.”
“Convert an amount between units.”
6 inputs, 3 required
amountnumberrequiredfromstringrequiredingredientstring or null“Needed for volume<->mass conversions (density is per-ingredient).”prepstring or nullregionstring or null“Region for cup/tbsp/tsp sizing: "us" (default), "uk", or "metric".”tostringrequired
“Nutrition facts for one ingredient amount (macros, micros, allergens, %DV).”
6 inputs, 2 required
amountnumberrequired“Quantity.”ingredientstringrequired“Ingredient name, e.g.”prepstring or null“Preparation, e.g.”referencestring or null“Reference-intake standard for %DV: "fda", "eu", or "uk".”regionstring or null“Region for cup/tbsp/tsp sizing: "us" (default), "uk", or "metric".”unitstring or null“Unit slug, e.g.”
“Convert a recipe web page, photos, or pasted text to Cooklang with cook.md.”
3 inputs
image_pathsarray or null“Photos of a recipe (cookbook page, card), as paths inside the recipe root.”textstring or null“Recipe text the user pasted.”urlstring or null“Recipe web page (http/https).”
“List the .cook recipes and .menu meal plans in the recipe collection.”
2 inputs
dirstring or null“Folder to list, relative to the recipe root.”kindstring or null“"recipe" (.cook), "menu" (.menu), "all" (default: both), or "template" for the .jinja report templates under reports/ and config/reports/.”
“Log in to cook.md.”
Takes no inputs.
“Fuzzy-search the ingredient catalog.”
2 inputs, 1 required
langstring or null“ISO 639-1 language code, default "en".”qstringrequired“Free-text ingredient name to fuzzy-match against the catalog.”
- pantry_depletedreads or searches
“Pantry items at or below their low-stock threshold.”
Takes no inputs.
- pantry_expiringreads or searches
“Pantry items expiring within `days` (default 7).”
1 input
daysinteger or null“Window in days.”
Show 12 more tools
- pantry_listreads or searches
“List what's in the pantry (config/pantry.conf), by section.”
1 input
sectionstring or null“Only this section, e.g.”
- pantry_recipesreads or searches
“What can I cook with what's in the pantry: recipes fully covered, and partial matches with the missing ingredients.”
1 input
thresholdinteger or null“Minimum % of a recipe's ingredients in stock to list it as a partial match.”
- pantry_updatecreates or changes datadescribed as changing data
“Add, update or remove pantry items in config/pantry.conf.”
3 inputs
addarrayremovearrayupdatearray
- read_recipereads or searches
“Read one recipe or meal plan: its Cooklang source plus the parsed ingredients, cookware, steps and metadata, optionally scaled.”
2 inputs, 1 required
pathstringrequired“Path relative to the recipe root, exactly as list_recipes/search_recipes returned it.”scalenumber or null“Scaling factor, e.g.”
- reference_intakesreads or searches
“Daily reference-intake tables (RDA/DV) for a standard: fda, eu, or uk.”
1 input
standardstring or null“"fda" (default), "eu", or "uk".”
- render_reporton 7 other servers
“Render a jinja report template against a .cook recipe or .menu plan.”
8 inputs
base_pathstring or null“Folder that `@./` references resolve from; default: the recipe root.”client_profile_pathstring or null“Path relative to the recipe root (absolute paths inside the root also work); a client profile YAML (dietary targets for checks).”inputstring or null“Inline cooklang source (requires `kind`).”input_pathstring or null“Path relative to the recipe root (absolute paths inside the root also work); a .cook recipe or .menu plan (kind inferred from extension).”kindstring or null“"cook" or "menu" — required with inline `input`.”scalenumber or null“Recipe scaling factor.”templatestring or null“Inline jinja template source.”template_pathstring or null“Path relative to the recipe root (absolute paths inside the root also work).”
“Search the recipe collection by words (matches names and contents) and/or a frontmatter tag.”
2 inputs
querystring“Words to match against recipe names and contents.”tagstring or null“Only recipes whose frontmatter `tags` contain this tag (case-insensitive).”
“Build a shopping list from recipes and/or .menu plans: merges duplicate ingredients, follows recipe references, groups by config/aisle.conf and subtracts config/pantry.conf.”
3 inputs, 1 required
formatstring or null“"json" (default, grouped by aisle) or "markdown".”ignore_pantryboolean or null“Don't subtract what config/pantry.conf already holds.”recipesarrayrequired“Recipes and/or .menu plans, relative to the recipe root.”
“Check Cooklang for errors: a file, a folder, unsaved `content`, or (no arguments) the whole collection.”
3 inputs
as_pathstring or null“With `content`: where it would be saved (decides .cook vs .menu and how `@./` references resolve).”contentstring or null“Unsaved Cooklang text to check instead of a file.”pathstring or null“A .cook/.menu file or a folder, relative to the recipe root.”
“Save config/aisle.conf (store aisles for shopping lists), config/pantry.conf (pantry stock; creates it if missing) or a jinja report template under reports/ or config/reports/ (path ending .jinja, re…”
2 inputs, 2 required
contentstringrequired“Full file content.”pathstringrequired“"config/aisle.conf", "config/pantry.conf", or a report template ending in .jinja under reports/ (CookCLI) or config/reports/ (Cook Editor), e.g.”
- write_menucreates or changes datadescribed as changing data
“Save a .menu meal plan.”
3 inputs, 2 required
contentstringrequired“Full file content.”forceboolean or null“Save even if validation finds errors.”pathstringrequired“Destination relative to the recipe root, e.g.”
- write_recipecreates or changes datadescribed as changing data
“Save a .cook recipe in the recipe collection.”
3 inputs, 2 required
contentstringrequired“Full file content.”forceboolean or null“Save even if validation finds errors.”pathstringrequired“Destination relative to the recipe root, e.g.”
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. 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 24 tools
- Says what it returns
- 100% of 15 tools
- States limits, defaults or errors
- 14% of 22 tools
- Says when to use it
- 27% of 22 tools
- Items covered per tool
- 2.2 of 4 on average
Counted from the listing
- Parameters with a description
- 85% of 60
- Tools with a description
- 100% of 24
- Typical description length
- 206 characters
The tool set
Counted from the listing
- Tools
- 24
- Size of the list
- about 4,235 tokens for an agent to load (characters ÷ 4)
- Naming
- 22 of 24 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 24 of 24 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 npm package @cookmd/mcp
Our sandbox started this package 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. The command runs the publisher’s code on your machine.
Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)
{
"mcpServers": {
"cook-mcp": {
"command": "npx",
"args": [
"-y",
"@cookmd/mcp@0.2.3"
]
}
}
}Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"cook-mcp": {
"command": "npx",
"args": [
"-y",
"@cookmd/mcp@0.2.3"
]
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"cook-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cookmd/mcp@0.2.3"
]
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"cook-mcp","type":"stdio","command":"npx","args":["-y","@cookmd/mcp@0.2.3"]}'Claude Code
claude mcp add --transport stdio cook-mcp -- npx -y @cookmd/mcp@0.2.3
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 -- npx -y @cookmd/mcp@0.2.3
- Optional settings the entry also lists (left out above): COOK_RECIPES_DIR.
- This runs the publisher's code on your machine (npx). Read its README first.
- 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.
Can it be installed, and is it up to date?
Version pin · advisories
Listed version
- Registry lists
- 0.2.3
- Latest stable
- 0.2.3
- Status
- current
- Withdrawn
- no
Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.
Dependency advisories
Counted in the full dependency tree as resolved on 2026-10-23 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).
Integrity, provenance, license
- Integrity
- sha512-vDO3o+RomH1iObtcQ…
- Signature
- signed and attested
- License
- MIT
Source: the package registry · 2026-10-23.
Usage
- Downloads
- 355 in the last month
Source: api.npmjs.org · 2026-10-23.
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 |
|---|---|---|---|
| Published package can be started | Started and answered | matches | our test · 2026-10-23 |
| Version 0.2.3 on npm | Exists and can be installed | matches | npm · 2026-10-23 |
| Repository github.com/cook-md/cook-mcp | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.cook-md
- GitHub owner
- an organization (cook-md)
- Build record
- signed and attested
- Repository
- github.com/cook-md/cook-mcp
- Stars
- 2
- Repository age
- 91–180 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)
Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Choosing
Record checks
Public records · not a safety rating8 of 9 record checks met
- #6,929 of 15,112 packages by monthly downloads, tied with 15 others
- Not ranked by stars: 2 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
- MetPackage names its licence with a standard (SPDX) identifierMIT
- MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
- Metnpm package carries build provenance (attestation)Signed, with a build attestation naming the source and workflow.
- MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. 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 io.github.cook-md/cook-mcp
Answered from the data aboveIs io.github.cook-md/cook-mcp safe to install?
We do not rate servers as safe or unsafe. 8 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its npm package carries a build-provenance attestation that names its source repository and build workflow. Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 7 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.
Is io.github.cook-md/cook-mcp free to use?
Its website (cook.md/pricing) describes a freemium pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.
Has io.github.cook-md/cook-mcp been security tested?
Partly. 4 of the 13 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.
What can io.github.cook-md/cook-mcp do?
It lists 24 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, generate content, calculate or convert and do something else. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.cook-md/cook-mcp change or delete data?
7 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.
Does io.github.cook-md/cook-mcp publish a security policy?
We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.
Is the listed version current?
Yes. The registry lists 0.2.3, the latest stable release on npm.
Where is the source code of io.github.cook-md/cook-mcp?
In github.com/cook-md/cook-mcp, which opens publicly.
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.
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
Not probed (read-only run)
We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. 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 applicable
- Consent handling: not applicable
- Sign-in metadata: not applicable
4 exercised9 not run (reason given)5 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 13 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
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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 package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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 package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.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
- 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
Source: our own test in an isolated sandbox, 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 the published package in an isolated sandbox (read-only mode)
- 1,684 msConnected after 0 redirects.
- Read the inventory: 24 tools, 17 resources, 8 prompts.
- 12,349 msFinished: 4 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.
“Free €0 forever”
“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. “io.github.cook-md/cook-mcp: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.cook-md/cook-mcp
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/io.github.cook-md/cook-mcp)
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