What's That Model? MCP server
com.whatsthatmodel/whats-that-modelwhatsthatmodel.comstreamable-httpv1.0.0Scanned
Sourced AI video/image capabilities, explained task recommendations and verified access context.
8 tools: 8 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 What's That Model? MCP server can do
The What's That Model? MCP server is published by whatsthatmodel.com, a domain the MCP Registry verified. It has 8 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
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.
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.
8 tools
Only reads 8Show 8 read-only tools
best_model_forGet an editorial shortlist for a known use case with verified constraints.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get an editorial shortlist for a known use case with verified constraints.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
compare_modelsCompare documented capabilities and task fit.No findings
Why it is in this group
- The name "compare_models" says "compare": a word for reading.
Description, as the server wrote it Compare documented capabilities and task fit. Unknowns stay explicit.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
find_modelFind an AI model by creation task and verified constraints.No findings
Why it is in this group
- The name "find_model" says "find": a word for reading.
Description, as the server wrote it Find an AI model by creation task and verified constraints. Editorial recommendation; not a benchmark score.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
get_modelGet model capabilities, dated citations, editorial limitations and labeled optional access link.No findings
Why it is in this group
- The name "get_model" says "get": a word for reading.
Description, as the server wrote it Get model capabilities, dated citations, editorial limitations and labeled optional access link.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
get_prompt_tipsGet untested prompting guidance, clearly distinguished from measured outputs.No findings
Why it is in this group
- The name "get_prompt_tips" says "get": a word for reading.
Description, as the server wrote it Get untested prompting guidance, clearly distinguished from measured outputs.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
get_trending_workflowsGet curated workflow spotlights; no unmeasured growth or income claims.No findings
Why it is in this group
- The name "get_trending_workflows" says "get": a word for reading.
Description, as the server wrote it Get curated workflow spotlights; no unmeasured growth or income claims.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
list_modelsList curated AI models including independent non-affiliate alternatives.No findings
Why it is in this group
- The name "list_models" says "list": a word for reading.
Description, as the server wrote it List curated AI models including independent non-affiliate alternatives.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
where_to_useReturn official and optional commercial access destinations, without guaranteeing plan entitlements.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return official and optional commercial access destinations, without guaranteeing plan entitlements.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
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, 18:50 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
- 0
- 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
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.
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 whats-that-model https://whatsthatmodel.com/mcpclaude mcp add --transport http whats-that-model https://whatsthatmodel.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__whats-that-model__find_model",
"mcp__whats-that-model__compare_models",
"mcp__whats-that-model__get_model",
"mcp__whats-that-model__best_model_for",
"mcp__whats-that-model__list_models",
"mcp__whats-that-model__where_to_use",
"mcp__whats-that-model__get_trending_workflows",
"mcp__whats-that-model__get_prompt_tips"
],
"ask": [],
"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 whats-that-model. 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/com.whatsthatmodel/whats-that-model/verify?hash=e13bf27cb3182c67e281c55dc0d01045cdce1ba0acfdf56302e6ada1eda3521d" | jq -e '.changed == false'Pinned hash e13bf27cb318, from Nov 14, 2026, 19:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.whatsthatmodel/whats-that-model/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.whatsthatmodel/whats-that-model)Source: MCP Registry. Synced Oct 21, 2026, 18:10 UTC.
What's That Model? MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the What's That Model? MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the What's That Model? MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the What's That Model? 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 What's That Model? MCP server have?
- 8 tools: 8 read. find_model, compare_models, get_model, best_model_for, list_models, where_to_use, get_trending_workflows and get_prompt_tips.
Does the What's That Model? MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the What's That Model? MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the What's That Model? MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.