Sous Chef MCP server
app.mysouschef/sous-chefmysouschef.appstreamable-httpv1.0.0Scanned
Save, import and edit recipes as interactive cards in ChatGPT and Claude, synced to your iPhone.
11 tools: 5 can delete or cancel things, 4 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Sous Chef MCP server can do
The Sous Chef MCP server is published by mysouschef.app, a domain the MCP Registry verified. It has 11 tools. It can delete or cancel things (5 tools: update_recipe, apply_recipe_patches, revert_recipe_edit, set_measurement_system and 1 more) and create or change data (4 tools: health_check, display_recipe, add_recipe and share_recipe). 2 tools only read.
1 tool brings in text other people can write (share_recipe).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
11 tools
Deletes or cancels 5Claude Code: deny
apply_recipe_patchesValidate and apply explicit edits.No findings
Why it is in this group
- The name "apply_recipe_patches" says "apply": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Validate and apply explicit edits. Pass recipeId for a persisted cooking session, or pass the full recipe payload from display_recipe to edit an unsaved card without persistence. Does NOT modify the saved recipe in your library.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
delete_recipePermanently delete a recipe owned by the authenticated user from their Sous Chef library.No findings
Why it is in this group
- The name "delete_recipe" says "delete": a word for removing or ending something.
- The description says "Permanently delete".
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Permanently delete a recipe owned by the authenticated user from their Sous Chef library. This cannot delete public catalog recipes.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
revert_recipe_editDrop a patch group by requestId.No findings
Why it is in this group
- The name "revert_recipe_edit" says "edit": a word for a change.
- The description's first verb is "drop": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Drop a patch group by requestId. Pass recipeId/sessionId for persisted edits, or pass the displayed card's baseRecipe and remaining patch history for a pure unsaved-card Undo. Unknown requestIds are idempotent no-ops.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
set_measurement_systemSet measurements without ingredient patches.No findings
Why it is in this group
- The name "set_measurement_system" says "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Set measurements without ingredient patches. Pass recipeId for saved session state, or pass the full recipe payload from display_recipe to update an unsaved card without persistence.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
update_recipeDeliberately updates allowed fields on a saved recipe in your library.No findings
Why it is in this group
- The name "update_recipe" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Deliberately updates allowed fields on a saved recipe in your library. Supports title, subtitle, summary, description, images, meta, and notes only; images and notes replace the whole array. Does not change ingredients or steps — use apply_recipe_patches for cooking-time edits in a session snapshot.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
Changes things 4Claude Code: ask
add_recipeCreates a NEW recipe in your library only when the user explicitly asks to save/add it or taps Save in the recipe card.No findings
Why it is in this group
- The name "add_recipe" says "add": a word for a change.
Description, as the server wrote it Creates a NEW recipe in your library only when the user explicitly asks to save/add it or taps Save in the recipe card. For a newly generated recipe the user has not chosen to keep, use display_recipe instead. Does not update existing recipes — to change a saved recipe use update_recipe. To make cooking-time tweaks use apply_recipe_patches. The server mints the stored import-* or ai-* recipe id; any caller-supplied recipe.id is treated only as source payload and is not used for upsert.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
display_recipePresents a complete recipe in Sous Chef's interactive recipe card (servings, ingredients, steps, cooking mode, validated edits, Undo).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Presents a complete recipe in Sous Chef's interactive recipe card (servings, ingredients, steps, cooking mode, validated edits, Undo). Prefer this over plain chat formatting whenever you generate, retrieve, or substantially revise a full recipe — including ordinary requests like 'give me a vegan mushroom carbonara' or 'make a quick dinner for two'. Displaying is temporary: it renders the card without saving it or creating a cooking session; saving only happens through add_recipe when the user asks.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
health_checkConfirm the Sous Chef MCP server is reachable.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Confirm the Sous Chef MCP server is reachable.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
get_recipeReturns the saved canonical recipe from your library or the public catalog.No findings
Why it is in this group
- The name "get_recipe" says "get": a word for reading.
Description, as the server wrote it Returns the saved canonical recipe from your library or the public catalog. In-progress cooking edits live in sessions and are not returned here.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_my_recipesList the authenticated user's saved Sous Chef recipes.No findings
Why it is in this group
- The name "list_my_recipes" says "list": a word for reading.
Description, as the server wrote it List the authenticated user's saved Sous Chef recipes. Use this before editing when the user refers to a recipe by name instead of id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 19, 2026, 17:22 UTC, unchanged since Nov 5, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 9
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.mysouschef.app/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://dev-zil2o04swu7qnals.us.auth0.com/
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 9 tools that change things (5 destructive, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.mysouschef.app/mcp: tools/list returned 11 tools to an anonymous client, including update_recipe (destructive), apply_recipe_patches (destructive), revert_recipe_edit (destructive), set_measurement_system (destructive), delete_recipe (destructive) and 4 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http sous-chef https://mcp.mysouschef.app/mcpclaude mcp add --transport http sous-chef https://mcp.mysouschef.app/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__sous-chef__list_my_recipes",
"mcp__sous-chef__get_recipe"
],
"ask": [
"mcp__sous-chef__health_check",
"mcp__sous-chef__display_recipe",
"mcp__sous-chef__add_recipe",
"mcp__sous-chef__share_recipe"
],
"deny": [
"mcp__sous-chef__update_recipe",
"mcp__sous-chef__apply_recipe_patches",
"mcp__sous-chef__revert_recipe_edit",
"mcp__sous-chef__set_measurement_system",
"mcp__sous-chef__delete_recipe"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as sous-chef. Review it before you use it.
Capability tags behind 1 rule
- mcp__sous-chef__share_recipe untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/app.mysouschef/sous-chef/verify?hash=f5ce8b286df13d199caa5e1433c0d31fe2fdacd512a1165cc9da1ebd48e63c49" | jq -e '.changed == false'Pinned hash f5ce8b286df1, from Nov 18, 2026, 12:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/app.mysouschef/sous-chef/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/app.mysouschef/sous-chef)Source: MCP Registry · repository. Synced Nov 4, 2026, 19:17 UTC.
Sous Chef MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Sous Chef MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 9 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Sous Chef MCP server delete data?
- Yes. 5 tools can delete, cancel or revoke something: update_recipe, apply_recipe_patches, revert_recipe_edit, set_measurement_system and delete_recipe.
Can the Sous Chef MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Sous Chef MCP server have?
- 11 tools: 5 destructive, 4 write, 2 read. update_recipe, apply_recipe_patches, revert_recipe_edit, set_measurement_system, delete_recipe, health_check, display_recipe, add_recipe and 3 more.
Does the Sous Chef MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Sous Chef MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Sous Chef MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.