Stovefront MCP server
com.stovefront/stovefrontstovefront.comstreamable-httpv1.0.0Scanned
Find US home kitchens on Stovefront, read their menus and pickup times, and build order links.
4 tools: 1 change things and 3 only read.
- Reads private data · 1
- Reads text others write · 0
- 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 Stovefront MCP server can do
The Stovefront MCP server is published by stovefront.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (1 tool: build_order_link), but cannot delete data. 3 tools only read.
1 tool reads private data (get_menu).
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 14, 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.
4 tools
Changes things 1Claude Code: ask
build_order_linkChecks that the given dishes can be ordered now in those quantities (stock, cutoff, quantity rules, one shared pickup time) and returns a link to the kitchen's own storefront with …1 finding
Why it is in this group
- The name "build_order_link" says "link": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "build_order_link" 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":false}; The name "build_order_link" says "link": a word for a change.
Description, as the server wrote it Checks that the given dishes can be ordered now in those quantities (stock, cutoff, quantity rules, one shared pickup time) and returns a link to the kitchen's own storefront with them already in the cart. It does not place an order or take payment: the customer reviews and submits the order request on the storefront, and the cook confirms it.
Annotations the server declares
- title: Build an order link
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 3Show 3 read-only tools
get_pickup_windowsReturns a kitchen's upcoming pickup and delivery times that are open for ordering, each with its order cutoff and the pickup place name.No findings
Why it is in this group
- The name "get_pickup_windows" says "get": a word for reading.
Description, as the server wrote it Returns a kitchen's upcoming pickup and delivery times that are open for ordering, each with its order cutoff and the pickup place name. Kitchens with scheduled times list each slot; kitchens with weekly pickup list each pickup time and the dishes it serves. Street addresses are never included.
Annotations the server declares
- title: Get pickup and delivery times
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_kitchensFinds published Stovefront kitchens and the dishes they have open for ordering.No findings
Why it is in this group
- The name "search_kitchens" says "search": a word for reading.
Description, as the server wrote it Finds published Stovefront kitchens and the dishes they have open for ordering. Matches words against kitchen names, dish names and categories, and can filter by dietary tags, pickup date and the area a kitchen serves. Returns each kitchen's name, storefront link, short description, service area and up to 8 matching dishes with price, dietary tags, stock and next pickup. Sample storefronts and kitchens hidden from search are not included.
Annotations the server declares
- title: Search kitchens
- 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 untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 16, 2026, 14:21 UTC, unchanged since Nov 2, 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
- 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 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://app.stovefront.com/mcp: tools/list returned 4 tools to an anonymous client, including build_order_link (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnbuild_order_link
The server marks "build_order_link" 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":false}; The name "build_order_link" says "link": a word for a change.
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 stovefront https://app.stovefront.com/mcpclaude mcp add --transport http stovefront https://app.stovefront.com/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__stovefront__search_kitchens",
"mcp__stovefront__get_menu",
"mcp__stovefront__get_pickup_windows"
],
"ask": [
"mcp__stovefront__build_order_link"
],
"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 stovefront. Review it before you use it.
Capability tags behind 1 rule
- mcp__stovefront__get_menu private-data
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/com.stovefront/stovefront/verify?hash=7a949b3a1eaa0b3de42928a9d213a489d8dd21b1b7c7a5881c3b38cfcebe8421" | jq -e '.changed == false'Pinned hash 7a949b3a1eaa, from Nov 14, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.stovefront/stovefront/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.stovefront/stovefront)Source: MCP Registry. Synced Nov 1, 2026, 20:17 UTC.
Stovefront MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Stovefront MCP server safe?
- No scan can promise that. What its definitions show: 4 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 Stovefront MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Stovefront 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 Stovefront MCP server have?
- 4 tools: 1 write, 3 read. build_order_link, search_kitchens, get_menu and get_pickup_windows.
Does the Stovefront MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Stovefront MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Stovefront MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.