readygpu: hardware for local AI MCP server
com.readygpu/readygpureadygpu.comstreamable-httpv1.0.0Scanned
Live UK, Germany, Canada and US prices for GPUs and Macs that run open AI models. No sign-up.
6 tools: 3 change things and 3 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 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 readygpu: hardware for local AI MCP server can do
The readygpu: hardware for local AI MCP server is published by readygpu.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (3 tools: hardware_details, hardware_for_model and best_hardware), but cannot delete data. 3 tools only read.
1 tool reads private data (search_models); 1 tool brings in text other people can write (search_models).
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 9, 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.
6 tools
Changes things 3Claude Code: ask
best_hardwareThe ranked 'best for local AI' lists of a market (all graphics cards, cards under a price, used cards, Macs and mini PCs): best first by the most capable model each runs fully in m…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 The ranked 'best for local AI' lists of a market (all graphics cards, cards under a price, used cards, Macs and mini PCs): best first by the most capable model each runs fully in memory. Prices are on each list's page.
Annotations the server declares
- title: Best hardware lists
- readOnlyHint: true
- openWorldHint: false
- idempotentHint: true
hardware_detailsOne graphics card or machine in a market: its specifications, which models it runs fully in memory at a context length and how fast, and a link to its page and prices.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 One graphics card or machine in a market: its specifications, which models it runs fully in memory at a context length and how fast, and a link to its page and prices.
Annotations the server declares
- title: Hardware details
- readOnlyHint: true
- openWorldHint: false
- idempotentHint: true
hardware_for_modelFor one model: how much memory it needs at each context length, and the fastest hardware (and the fastest Mac) that runs it fully in memory in a market, with their speeds.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 For one model: how much memory it needs at each context length, and the fastest hardware (and the fastest Mac) that runs it fully in memory in a market, with their speeds. Links the model's page, which shows the cheapest and best-value picks with prices.
Annotations the server declares
- title: Hardware to run a model
- readOnlyHint: true
- openWorldHint: false
- idempotentHint: true
Only reads 3Show 3 read-only tools
compare_hardwareTwo graphics cards or machines side by side in a market: memory, bandwidth, how many models each runs fully in memory, and the estimated speed of each on every model.No findings
Why it is in this group
- The name "compare_hardware" says "compare": a word for reading.
Description, as the server wrote it Two graphics cards or machines side by side in a market: memory, bandwidth, how many models each runs fully in memory, and the estimated speed of each on every model.
Annotations the server declares
- title: Compare two
- readOnlyHint: true
- openWorldHint: false
- idempotentHint: true
find_hardwareList graphics cards or complete machines (Macs, mini PCs) sold in a market, with memory, bandwidth, the estimated speed on a model and a link to each one's page and prices.No findings
Why it is in this group
- The name "find_hardware" says "find": a word for reading.
Description, as the server wrote it List graphics cards or complete machines (Macs, mini PCs) sold in a market, with memory, bandwidth, the estimated speed on a model and a link to each one's page and prices. Filter by minimum memory and new or used; sort by speed or popularity.
Annotations the server declares
- title: Find graphics cards or machines
- readOnlyHint: true
- openWorldHint: false
- idempotentHint: true
search_modelsFind open-weight AI models by name or task (chat, coding, agentic, vision, reasoning).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search_models" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "find" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "find" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Find open-weight AI models by name or task (chat, coding, agentic, vision, reasoning). Returns each model's slug, size, context length and licence; use the slug with hardware_for_model.
Annotations the server declares
- title: Search open models
- readOnlyHint: true
- openWorldHint: 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 outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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 18, 2026, 16:23 UTC, unchanged since Oct 27, 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
- 3
- 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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://readygpu.com/api/mcp: tools/list returned 6 tools to an anonymous client, including hardware_details (write), hardware_for_model (write), best_hardware (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:best_hardwareChanges thingsdescriptioninputSchema
- Changed:compare_hardwareOnly readsdescriptioninputSchema
- Changed:find_hardwareOnly readsdescriptioninputSchema
- Changed:hardware_detailsChanges thingsdescriptioninputSchema
- Changed:hardware_for_modelChanges thingsdescriptioninputSchema
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http readygpu https://readygpu.com/api/mcpclaude mcp add --transport http readygpu https://readygpu.com/api/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__readygpu__search_models",
"mcp__readygpu__find_hardware",
"mcp__readygpu__compare_hardware"
],
"ask": [
"mcp__readygpu__hardware_details",
"mcp__readygpu__hardware_for_model",
"mcp__readygpu__best_hardware"
],
"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 readygpu. Review it before you use it.
Capability tags behind 1 rule
- mcp__readygpu__search_models private-data, untrusted-input
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.readygpu/readygpu/verify?hash=2a5b39841a34d5358297eecaa786e2751833fffcb70e55a5af1df2be5f069c48" | jq -e '.changed == false'Pinned hash 2a5b39841a34, from Nov 9, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.readygpu/readygpu/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.readygpu/readygpu)Source: MCP Registry. Synced Oct 27, 2026, 07:17 UTC.
readygpu: hardware for local AI MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the readygpu: hardware for local AI MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 3 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 readygpu: hardware for local AI MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the readygpu: hardware for local AI 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 readygpu: hardware for local AI MCP server have?
- 6 tools: 3 write, 3 read. hardware_details, hardware_for_model, best_hardware, search_models, find_hardware and compare_hardware.
Does the readygpu: hardware for local AI MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the readygpu: hardware for local AI MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the readygpu: hardware for local AI MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.