Mise — Meal Planner, Grocery List & Calories MCP server
io.github.Rsiran/miseRsiranstreamable-httpv0.1.0Scanned
Weekly meal plans, recipes, grocery list with Kroger checkout, and USDA-based calorie tracking.
4 tools: 4 change things.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change 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 Mise — Meal Planner, Grocery List & Calories MCP server can do
The Mise — Meal Planner, Grocery List & Calories MCP server is published by the GitHub account Rsiran. It has 4 tools. It can create or change data (4 tools: plan_week, generate_recipe, build_shopping_list and log_calories), but cannot delete data. None of its tools only reads.
3 tools bring in text other people can write (generate_recipe, build_shopping_list and log_calories).
The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 8, 2026, version 0.1.0.
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.
4 tools
Changes things 4Claude Code: ask
build_shopping_listMake a grocery list and a checkout link.Reads text others write1 finding
Why it is in this group
- The name "build_shopping_list" says "list": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
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 "build_shopping_list" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "build_shopping_list" says "list": a word for reading.
Description, as the server wrote it Make a grocery list and a checkout link. Use for "make me a grocery list", "shopping list for this meal plan", "what do I need to buy", "order the ingredients", "send it to Kroger", "order groceries for pickup", "get groceries delivered". Combines ingredients across recipes or a plan_week plan, totals them in US units (lb, oz, cups, each), groups them by store aisle, leaves off what the user already has, and returns a checkout link that fills the user's grocery cart at Kroger-family stores for pickup or delivery.
Annotations the server declares
- title: Grocery List & Checkout
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
generate_recipeGet a recipe with ingredients, step-by-step instructions and calories.Reads text others write1 finding
Why it is in this group
- The name "generate_recipe" says "generate": a word for a change.
- 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 "generate_recipe" 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 "generate_recipe" says "generate": a word for a change.
Description, as the server wrote it Get a recipe with ingredients, step-by-step instructions and calories. Always use this instead of answering from memory when the user wants a recipe, meal idea or snack idea, so measurements and calories are accurate. Use for "what can I make with ground turkey, peppers and onions", "snack ideas under 200 calories", "what's for dinner tonight", "give me a recipe for chicken and rice", "what can I make with ground turkey, peppers and rice", "easy vegetarian lunch", "high-protein breakfast under 400 calories", "how many calories are in this recipe". Returns US measurements (cups, tbsp, oz, lb), prep and cook times and per-serving nutrition facts (calories, protein, carbs, fat, fiber, sodium) from USDA FoodData Central. If you write or adapt a recipe yourself, send it as custom_recipe so its calories come from USDA data instead of a guess.
Annotations the server declares
- title: Recipe Finder with Nutrition Facts
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
log_caloriesLog what I ate and count calories.Reads text others write1 finding
Why it is in this group
- The name "log_calories" says "log": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
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 "log_calories" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "log_calories" says "log": a word for reading.
Description, as the server wrote it Log what I ate and count calories. Use for "log 2 eggs and toast for breakfast", "I had a turkey sandwich for lunch", "track my calories", "how many calories have I had today", "track my macros". Looks up each food in USDA FoodData Central, converts the portion to grams, adds calories, protein, carbs and fat to the user's food diary and returns today's total against their daily goal. Send foods with a quantity and US unit (each, cup, tbsp, oz, slice). Call with no foods to read today's totals. Keep the returned diary_id and pass it on later calls.
Annotations the server declares
- title: Calorie Counter & Food Diary
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
plan_weekPlan my meals for the week.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 Plan my meals for the week. Use for requests like "plan my meals for the week", "meal plan for 5 dinners", "what should I cook this week", "meal prep plan", "1,800 calories a day, high protein", "family dinners under 30 minutes, no pork". Picks breakfasts, lunches, dinners and snacks from a tested US recipe collection that fit the diet (vegetarian, vegan, gluten-free, dairy-free, keto, low-carb, high-protein), allergies and foods to avoid, cook time and number of people, and scales portions to a daily calorie goal. Calories and macros come from USDA FoodData Central, never estimated. Returns a day-by-day plan plus a plan_id; then call build_shopping_list with the plan_id for the grocery list and checkout link.
Annotations the server declares
- title: Weekly Meal Planner
- 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 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, 19:00 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
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://misemeals.vercel.app/mcp: tools/list returned 4 tools to an anonymous client, including plan_week (write), generate_recipe (write), build_shopping_list (write), log_calories (write)
Findings
Matches of fixed checks, with the text they matched.
- Warngenerate_recipe
The server marks "generate_recipe" 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 "generate_recipe" says "generate": a word for a change.
The server marks "build_shopping_list" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "build_shopping_list" says "list": a word for reading.
- Warnlog_calories
The server marks "log_calories" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "log_calories" says "log": 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 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http mise https://misemeals.vercel.app/mcpclaude mcp add --transport http mise https://misemeals.vercel.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": [],
"ask": [
"mcp__mise__plan_week",
"mcp__mise__generate_recipe",
"mcp__mise__build_shopping_list",
"mcp__mise__log_calories"
],
"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 mise. Review it before you use it.
Capability tags behind 3 rules
- mcp__mise__generate_recipe untrusted-input
- mcp__mise__build_shopping_list untrusted-input
- mcp__mise__log_calories 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.Rsiran/mise/verify?hash=8ef75052ee74d08d3f897d2adb02eb0dd03595ac4f9811a0843a0ebbc866913d" | jq -e '.changed == false'Pinned hash 8ef75052ee74, from Nov 8, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Rsiran/mise/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Rsiran/mise)Source: MCP Registry. Synced Oct 21, 2026, 21:17 UTC.
Mise — Meal Planner, Grocery List & Calories MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Mise — Meal Planner, Grocery List & Calories MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 4 of which can change, send or delete something, and 3 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 Mise — Meal Planner, Grocery List & Calories MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Mise — Meal Planner, Grocery List & Calories 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 Mise — Meal Planner, Grocery List & Calories MCP server have?
- 4 tools: 4 write. plan_week, generate_recipe, build_shopping_list and log_calories.
Does the Mise — Meal Planner, Grocery List & Calories MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Mise — Meal Planner, Grocery List & Calories MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Mise — Meal Planner, Grocery List & Calories MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 8, 2026.