Recall365 — Global Product Recalls MCP server
io.recall365/recall365recall365.iostreamable-httpv1.0.1Scanned
Search official product recalls from US, EU, UK, CA, AU, JP, KR, CN regulators and FDA red lists.
6 tools: 4 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding
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 Recall365 — Global Product Recalls MCP server can do
The Recall365 — Global Product Recalls MCP server is published by recall365.io, a domain the MCP Registry verified. It has 6 tools. It can create or change data (4 tools: brand_recall_history, precheck_product, fda_import_alerts and data_coverage), but cannot delete data. 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
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 21, 2026, version 1.0.1.
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.
6 tools
Changes things 4Claude Code: ask
brand_recall_historyRecall history of a brand across all markets: totals by year, country and category, plus the 10 latest notices.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 Recall history of a brand across all markets: totals by year, country and category, plus the 10 latest notices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
data_coverageWhich official sources are covered, record counts, and the latest publish date per source (how fresh the data is).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 Which official sources are covered, record counts, and the latest publish date per source (how fresh the data is).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
fda_import_alertsSearch the FDA Import Alert red lists: firms whose products can be detained at the US border without physical examination.1 finding
Why it is in this group
- The name "fda_import_alerts" says "import": 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 "fda_import_alerts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "fda_import_alerts" says "import": a word for a change.
Description, as the server wrote it Search the FDA Import Alert red lists: firms whose products can be detained at the US border without physical examination. Search by firm name, city or product (e.g. 'laser', 'eye shadow', 'Shenzhen'). Defaults to firms in China.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
precheck_productRisk profile for a product type before selling it abroad: recalls in the last 3 years, share made in China, top hazards, top markets, yearly trend, typical cases and self-check adv…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 Risk profile for a product type before selling it abroad: recalls in the last 3 years, share made in China, top hazards, top markets, yearly trend, typical cases and self-check advice.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
get_recallFull detail of one recall by its Recall365 id: product, brand, hazard, failed standards, remedy, official notice link.No findings
Why it is in this group
- The name "get_recall" says "get": a word for reading.
Description, as the server wrote it Full detail of one recall by its Recall365 id: product, brand, hazard, failed standards, remedy, official notice link.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
search_recallsSearch official product recalls by keyword (product, brand, hazard; Chinese/English/Korean brand names are cross-matched).No findings
Why it is in this group
- The name "search_recalls" says "search": a word for reading.
Description, as the server wrote it Search official product recalls by keyword (product, brand, hazard; Chinese/English/Korean brand names are cross-matched). Returns at most 20 newest/most relevant notices with links.
Annotations the server declares
- readOnlyHint: 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 untrusted-input or outbound.
- Reads private data0
- 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 20, 2026, 18:20 UTC, unchanged since Nov 20, 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://app.recall365.io/mcp: tools/list returned 6 tools to an anonymous client, including brand_recall_history (write), precheck_product (write), fda_import_alerts (write), data_coverage (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "fda_import_alerts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "fda_import_alerts" says "import": 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 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http recall365 https://app.recall365.io/mcpclaude mcp add --transport http recall365 https://app.recall365.io/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__recall365__search_recalls",
"mcp__recall365__get_recall"
],
"ask": [
"mcp__recall365__brand_recall_history",
"mcp__recall365__precheck_product",
"mcp__recall365__fda_import_alerts",
"mcp__recall365__data_coverage"
],
"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 recall365. Review it before you use it.
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.recall365/recall365/verify?hash=0eef08fceae23f9d2e19d0f1dffea82780c9698676f2e41b7c611df07a591f50" | jq -e '.changed == false'Pinned hash 0eef08fceae2, from Nov 21, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.recall365/recall365/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.recall365/recall365)Source: MCP Registry. Synced Nov 21, 2026, 14:18 UTC.
Recall365 — Global Product Recalls MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Recall365 — Global Product Recalls MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 4 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 Recall365 — Global Product Recalls MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Recall365 — Global Product Recalls 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 Recall365 — Global Product Recalls MCP server have?
- 6 tools: 4 write, 2 read. brand_recall_history, precheck_product, fda_import_alerts, data_coverage, search_recalls and get_recall.
Does the Recall365 — Global Product Recalls MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Recall365 — Global Product Recalls MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Recall365 — Global Product Recalls MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.