Rattlewatch MCP server
io.github.veritylabsai/rattlewatchveritylabsaistreamable-httpv0.2.1Scanned
Cited US recall lookup for AI agents: CPSC and FDA data, nothing invented.
4 tools: 1 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
1 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Rattlewatch MCP server can do
The Rattlewatch MCP server is published by the GitHub account veritylabsai. It has 4 tools. It can create or change data (1 tool: verify), but cannot delete data. 3 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Nov 6, 2026, version 0.2.1.
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.
4 tools
Changes things 1Claude Code: ask
verifyCheck a claim or product query against the store.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 Check a claim or product query against the store. Returns only cited records (recalls and requirements) that match. Explicitly reports 'no verified record' when nothing matches -- it never synthesizes an answer, so absence means 'not in the store', not a negative claim.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- readOnlyHint: true
- title: Verify a claim
Only reads 3Show 3 read-only tools
get_requirementGet cited market-entry requirements for a product subject in a given market (e.g.No findings
Why it is in this group
- The name "get_requirement" says "get": a word for reading.
Description, as the server wrote it Get cited market-entry requirements for a product subject in a given market (e.g. subject='childrens_products', market='US'). This is a small curated set, not a full regulatory database: CPC, CPSC eFiling, EU GPSR, CE marking, REACH SVHC, RoHS and California Prop 65. Returns each fact with its official citation URL and last-verified date.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- readOnlyHint: true
- title: Get requirement
list_changesList recall and requirement changes since an ISO-8601 timestamp (e.g.No findings
Why it is in this group
- The name "list_changes" says "list": a word for reading.
Description, as the server wrote it List recall and requirement changes since an ISO-8601 timestamp (e.g. '2026-09-01T00:00:00+00:00'). Includes newly published recalls and rule changes, each with its source URL.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- readOnlyHint: true
- title: List changes
search_recallsSearch official US recall records by product name, brand, model, or UPC.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 US recall records by product name, brand, model, or UPC. Covers CPSC consumer products and FDA food, drug and device enforcement. Returns only cited records from the store, each with a source URL and a match score. If nothing matches, returns an empty list rather than guessing.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- readOnlyHint: true
- title: Search recalls
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, 19:12 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: The operation was aborted due to timeout
Posture changes
- Nov 13, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
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.
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 1 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 0.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http rattlewatch https://rattlewatch.rattled.ca/mcpclaude mcp add --transport http rattlewatch https://rattlewatch.rattled.ca/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__rattlewatch__search_recalls",
"mcp__rattlewatch__get_requirement",
"mcp__rattlewatch__list_changes"
],
"ask": [
"mcp__rattlewatch__verify"
],
"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 rattlewatch. 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.github.veritylabsai/rattlewatch/verify?hash=3982b6400f3237e2f434a20df36a6ecb61aedfb8a7573ce6f95a817bd786f6fb" | jq -e '.changed == false'Pinned hash 3982b6400f32, from Nov 6, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.veritylabsai/rattlewatch/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.veritylabsai/rattlewatch)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:51 UTC.
Rattlewatch MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Rattlewatch MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 1 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 Rattlewatch MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Rattlewatch 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 Rattlewatch MCP server have?
- 4 tools: 1 write, 3 read. verify, search_recalls, get_requirement and list_changes.
Does the Rattlewatch MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Rattlewatch MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Rattlewatch MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 6, 2026.