AI Deprecations MCP server
com.aideprecations/ai-deprecationsaideprecations.comstreamable-httpv1.3.0Scanned
AI model shutdown dates, replacements, change feed and webhook alerts for 8 providers.
8 tools: 2 change things and 6 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 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 AI Deprecations MCP server can do
The AI Deprecations MCP server is published by aideprecations.com, a domain the MCP Registry verified. It has 8 tools. It can create or change data (2 tools: subscribe_alerts and unsubscribe), but cannot delete data. 6 tools only read.
1 tool can send data out of your system (subscribe_alerts).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 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.
8 tools
Changes things 2Claude Code: ask
subscribe_alertsSubscribe to deprecation/shutdown change alerts, with the user's consent.Can send data outNo findings
Why it is in this group
- The name "subscribe_alerts" says "subscribe": a word for a change.
What it can reach
- outboundThe input takes a URL (input.webhook): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Subscribe to deprecation/shutdown change alerts, with the user's consent. Give a public https webhook URL (JSON POST on every change, checked daily) or an email (double opt-in; email only when a model is being retired, no digest). Optional providers filter. Returns an unsubscribe token for webhooks.
unsubscribeStop webhook alerts using the token from subscribe_alerts.No findings
Why it is in this group
- The name "unsubscribe" says "unsubscribe": a word for a change.
Description, as the server wrote it Stop webhook alerts using the token from subscribe_alerts. Email subscribers unsubscribe from the link in any email.
Only reads 6Show 6 read-only tools
get_changes_sinceList tracked AI model records whose status, deprecation/shutdown date, replacement or source changed since an ISO 8601 time.No findings
Why it is in this group
- The name "get_changes_since" says "get": a word for reading.
Description, as the server wrote it List tracked AI model records whose status, deprecation/shutdown date, replacement or source changed since an ISO 8601 time. Poll this to stay current: on later calls pass the previous response's checked_at. History starts at tracking_since; an earlier since returns a warning (count 0 then does not mean nothing changed).
get_coveragePer-provider coverage today: rows with a known shutdown date, rows where the vendor page gives no date, rows not verified today, and official pages that could not be read today.No findings
Why it is in this group
- The name "get_coverage" says "get": a word for reading.
Description, as the server wrote it Per-provider coverage today: rows with a known shutdown date, rows where the vendor page gives no date, rows not verified today, and official pages that could not be read today. Also returns manual source reviews (a person checking a page the parser could not read; empty until one is recorded) and the replacement_kind rule.
get_providerAll tracked models for one provider (openai, anthropic, google-gemini, google-vertex, azure-openai, aws-bedrock, mistral, cohere).No findings
Why it is in this group
- The name "get_provider" says "get": a word for reading.
Description, as the server wrote it All tracked models for one provider (openai, anthropic, google-gemini, google-vertex, azure-openai, aws-bedrock, mistral, cohere). Includes an alerts signup offer (?src=mcp) and a pointer to subscribe_alerts (sign a user up only with their consent).
get_shutdown_dateGet the official deprecation/shutdown date, replacement and source for an AI model ID (e.g.No findings
Why it is in this group
- The name "get_shutdown_date" says "get": a word for reading.
Description, as the server wrote it Get the official deprecation/shutdown date, replacement and source for an AI model ID (e.g. gpt-4o-2024-08-06, claude-sonnet-4-5). Includes an alerts signup offer (?src=mcp) and a pointer to subscribe_alerts (sign a user up only with their consent).
list_upcomingList AI model shutdowns in the next N days, soonest first.No findings
Why it is in this group
- The name "list_upcoming" says "list": a word for reading.
Description, as the server wrote it List AI model shutdowns in the next N days, soonest first. Includes an alerts signup offer (?src=mcp) and a pointer to subscribe_alerts (sign a user up only with their consent).
search_modelsSearch all tracked AI models (including retired) by name.No findings
Why it is in this group
- The name "search_models" says "search": a word for reading.
Description, as the server wrote it Search all tracked AI models (including retired) by name. Includes an alerts signup offer (?src=mcp) and a pointer to subscribe_alerts (sign a user up only with their consent).
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.
- 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 out1
- 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 21, 2026, 19:21 UTC, unchanged since Nov 7, 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
- 2
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.aideprecations.com/mcp: tools/list returned 8 tools to an anonymous client, including subscribe_alerts (write), unsubscribe (write)
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.
Tools5 changed.~5 changedView diff
- Changed:get_providerOnly readsdescription
- Changed:get_shutdown_dateOnly readsdescription
- Changed:list_upcomingOnly readsdescription
- Changed:search_modelsOnly readsdescription
- Changed:subscribe_alertsChanges thingsdescription
Install
Pinned to version 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http ai-deprecations https://mcp.aideprecations.com/mcpclaude mcp add --transport http ai-deprecations https://mcp.aideprecations.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__ai-deprecations__get_shutdown_date",
"mcp__ai-deprecations__list_upcoming",
"mcp__ai-deprecations__search_models",
"mcp__ai-deprecations__get_provider",
"mcp__ai-deprecations__get_changes_since",
"mcp__ai-deprecations__get_coverage"
],
"ask": [
"mcp__ai-deprecations__subscribe_alerts",
"mcp__ai-deprecations__unsubscribe"
],
"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 ai-deprecations. Review it before you use it.
Capability tags behind 1 rule
- mcp__ai-deprecations__subscribe_alerts outbound
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.aideprecations/ai-deprecations/verify?hash=56a4c365899da4f497b7904a425cadf38831d6f69661f6d3b4e3f55a478fb201" | jq -e '.changed == false'Pinned hash 56a4c365899d, from Nov 20, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.aideprecations/ai-deprecations/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.aideprecations/ai-deprecations)Source: MCP Registry. Synced Nov 6, 2026, 06:17 UTC.
AI Deprecations MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AI Deprecations MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 2 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 AI Deprecations MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AI Deprecations 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 AI Deprecations MCP server have?
- 8 tools: 2 write, 6 read. subscribe_alerts, unsubscribe, get_shutdown_date, list_upcoming, search_models, get_provider, get_changes_since and get_coverage.
Does the AI Deprecations MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AI Deprecations MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): subscribe_alerts.
Has the AI Deprecations MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.