Plate Pal MCP server
io.github.GoodTurnStudio/platepalGoodTurnStudiostreamable-httpv1.3.0Scanned
Calories and nutrition for any food, chain meal or barcode, and meal ideas for a goal and diet.
3 tools: 1 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- 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 Plate Pal MCP server can do
The Plate Pal MCP server is published by the GitHub account GoodTurnStudio. It has 3 tools. It can create or change data (1 tool: get_barcode_nutrition), but cannot delete data. 2 tools only read.
3 tools bring in text other people can write (get_food_nutrition, get_barcode_nutrition and get_meal_ideas).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 17, 2026, version 1.3.0.
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.
3 tools
Changes things 1Claude Code: ask
get_barcode_nutritionNutrition for a packaged product by barcode, with UK traffic lights.Reads text others write1 finding
Why it is in this group
- The name "get_barcode_nutrition" says "get": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "get_barcode_nutrition" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "get_barcode_nutrition" says "get": a word for reading.
Description, as the server wrote it Nutrition for a packaged product by barcode, with UK traffic lights. For requests like "is this barcode high in sugar?", "how many calories in this?" after a scan, or "what's the salt in 5000157024886?". Returns per 100 g (or 100 ml) and per serving values, traffic lights for fat, saturates, sugars and salt, Nutri-Score, allergens and a Halal or Not? link for checking the ingredients.
Annotations the server declares
- title: Nutrition for a packaged product by barcode, with UK traffic lights
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
get_food_nutritionCalories and macros for a food, dish or product, for the amount the user says.Reads text others writeNo findings
Why it is in this group
- The name "get_food_nutrition" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Calories and macros for a food, dish or product, for the amount the user says. For requests like "how many calories in a Big Mac?", "protein in 200g chicken breast", "calories in chicken biryani", "a slice of pepperoni pizza", "a large latte" or a whole meal like "2 eggs, 2 slices of toast and a coffee". Takes the whole amount and food in q, or grams or servings separately. Generic foods and dishes (thousands, including fast food and restaurant dishes) use USDA values with real portion weights (slice, cup, small, medium, large, one item); brands come from Open Food Facts. Chain items ("McDonald's large fries", "a Greggs sausage roll", "KFC Zinger burger", "grande latte from Starbucks", "6 inch Italian BMT from Subway", "20 piece McNuggets") use the chain's own published figures for that size, UK or US by country, and return a chain object (name, region, item, size, weight_published); when the chain doesn't publish a weight, amount.grams is null and per_100 values are null. For a chain item not in the table, a typical USDA version is used and the say line says so. A whole meal returns items (each food with its amount and nutrition) and total. Returns nutrition for the amount, per_100 values, portions, UK traffic lights (per 100 g, or per 100 ml for drinks) and caffeine_mg for drinks that have it.
Annotations the server declares
- title: Calories and macros for a food, dish or product, for the amount the user says
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_meal_ideasSimple meal ideas by goal, diet and meal, with rough macros.Reads text others writeNo findings
Why it is in this group
- The name "get_meal_ideas" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Simple meal ideas by goal, diet and meal, with rough macros. For requests like "give me a high protein halal dinner idea", "a quick vegan lunch", "cheap vegetarian breakfast ideas". Goals: high protein, low carb, budget, quick, high fibre. Diets: vegetarian, vegan, pescatarian, halal. Meals: breakfast, lunch, dinner, snack. The user's words can go in q instead. Ideas rotate daily. It does not set calorie or weight targets; a weight-loss request gets lighter, filling ideas (goal lighter, 450 calories or less) and a pointer to a doctor or dietitian, with no shop links.
Annotations the server declares
- title: Simple meal ideas by goal, diet and meal, with rough macros
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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 write3
- 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 20, 2026, 19:29 UTC, unchanged since Oct 22, 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
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://goodturn-mcp.pages.dev/.well-known/oauth-protected-resource/platepal/mcp
- Authorization servers
- https://jobspotter.pages.dev
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://goodturn-mcp.pages.dev/platepal/mcp: tools/list returned 3 tools to an anonymous client, including get_barcode_nutrition (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "get_barcode_nutrition" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "get_barcode_nutrition" says "get": a word for reading.
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 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http platepal https://goodturn-mcp.pages.dev/platepal/mcpclaude mcp add --transport http platepal https://goodturn-mcp.pages.dev/platepal/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__platepal__get_food_nutrition",
"mcp__platepal__get_meal_ideas"
],
"ask": [
"mcp__platepal__get_barcode_nutrition"
],
"deny": []
}
}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 platepal. Review it before you use it.
Capability tags behind 3 rules
- mcp__platepal__get_food_nutrition untrusted-input
- mcp__platepal__get_barcode_nutrition untrusted-input
- mcp__platepal__get_meal_ideas 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/io.github.GoodTurnStudio/platepal/verify?hash=825f78f3c10781d5197d034968c648eaa8e8c6183a1d3aa8e71686a825b841f6" | jq -e '.changed == false'Pinned hash 825f78f3c107, from Nov 17, 2026, 22:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.GoodTurnStudio/platepal/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.GoodTurnStudio/platepal)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:16 UTC.
Plate Pal MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Plate Pal MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Plate Pal MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Plate Pal 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 Plate Pal MCP server have?
- 3 tools: 1 write, 2 read. get_barcode_nutrition, get_food_nutrition and get_meal_ideas.
Does the Plate Pal MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Plate Pal MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Plate Pal MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.