Skip to content

modelread MCP server

com.modelread/modelreadmodelread.comstreamable-httpv0.3.1Scanned

Will this Hugging Face model run on my hardware? Fit, best quant, tok/s range, launch command.

6 tools: 3 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 3 write, 3 read.
  • Reads private data · 1
  • Reads text others write · 5
  • Can send data out · 0
  • 1 finding

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.
Govern this server →

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 modelread MCP server can do

The modelread MCP server is published by modelread.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (3 tools: estimate_fit, compare_hardware and ask), but cannot delete data. 3 tools only read.

1 tool reads private data (compare_hardware); 5 tools bring in text other people can write (estimate_fit, compare_hardware, find_models and 2 more).

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 18, 2026, version 0.3.1.

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 3Claude Code: ask
  • askFree-form question about running Hugging Face models locally or self-hosted (runtimes, quant choice, KV cache, why something OOMs, MoE offload); returns markdown plus the parsed qu…Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Free-form question about running Hugging Face models locally or self-hosted (runtimes, quant choice, KV cache, why something OOMs, MoE offload); returns markdown plus the parsed query and notes. Prefer estimate_fit / find_models when the question is one of those.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Ask about running models
  • compare_hardwareRun one repo against several devices and return the best candidate per device (verdict, quant, decode band, max context, launch command), sorted best first.Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "compare_hardware" says "compare": a word for reading.
    • The description's first verb is "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • private-dataThe description's first sentence says "repo": it reads repositories.
    • private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "compare_hardware" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "compare_hardware" says "compare": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Run one repo against several devices and return the best candidate per device (verdict, quant, decode band, max context, launch command), sorted best first. Use for 'which of my machines should run X' or 'is a 4090 or an M4 Max better for X'. hardware: comma-separated list of presets / free text (max 8).

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Compare one model across devices
  • estimate_fitWill this Hugging Face repo run on this hardware?Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Will this Hugging Face repo run on this hardware? Checks the repo and its quantized derivatives (GGUF/MLX/AWQ...) and returns, per candidate: verdict (fits | fits-tight | offload | no | unknown), memory placement (VRAM / RAM / SSD), longest context that fits, decode and prefill tok/s bands with basis, concurrent-serving aggregate, runtime support (llama.cpp / vLLM / MLX registries) and an exact launch command. repo: 'org/name' (base model or a GGUF repo). hardware: preset id, '<N>x-<id>', free text, or 'gpu=..,ram=..,bw=..'. ctx in tokens.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Estimate model fit and speed
Only reads 3Show 3 read-only tools
  • find_modelsRecommend models for a task on given hardware, written as a natural question, e.g.Reads text others writeNo findings

    Why it is in this group

    • The name "find_models" says "find": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Recommend models for a task on given hardware, written as a natural question, e.g. 'best coding model for an RTX 4090 + 64GB RAM at 32k context', 'Japanese chat on a Galaxy S25 Ultra', 'serve 8 users on 2x RTX 3090'. Ranks indexed Hub models (~20k, refreshed nightly) by fit, task benchmark percentile (provenance-tagged, vendor vs independent), speed and adoption; each result carries a full fit estimate. Tasks understood: chat, coding, agentic, vision, ocr, math, reasoning, multilingual, function-calling, embedding, reranking, speech-to-text, tts, image-generation, video-generation.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Find the best models for a device
  • list_hardwareList hardware presets (330+: GPUs of every vendor and segment, multi-GPU nodes, Apple, Jetson/APUs, phones, tablets, SBCs, VPS tiers).No findings

    Why it is in this group

    • The name "list_hardware" says "list": a word for reading.
    Description, as the server wrote it
    List hardware presets (330+: GPUs of every vendor and segment, multi-GPU nodes, Apple, Jetson/APUs, phones, tablets, SBCs, VPS tiers). filter: words matched against id/name/vendor/segment, e.g. 'h100', 'amd datacenter', 'phone samsung', 'vps'. Returns id, name, kind, memory, bandwidth, backend.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List hardware presets
  • search_modelsSearch the model index without estimating (fast): ids, task, library, params, downloads, likes, license, created date.Reads text others writeNo findings

    Why it is in this group

    • The name "search_models" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Search the model index without estimating (fast): ids, task, library, params, downloads, likes, license, created date. task: chat|coding|vision|embedding|... ; query: substring of the repo id (e.g. 'qwen3', 'gemma-4'); max_params_billion filters by size.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Search the model index

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 write5
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.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:19 UTC, unchanged since Nov 19, 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.

    Matched text

    https://modelread.com/mcp: tools/list returned 6 tools to an anonymous client, including estimate_fit (write), compare_hardware (write), ask (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "compare_hardware" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "compare_hardware" says "compare": a word for reading.

    What this check looks for

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 0.3.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http modelread https://modelread.com/mcp
claude mcp add --transport http modelread https://modelread.com/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__modelread__find_models",
      "mcp__modelread__search_models",
      "mcp__modelread__list_hardware"
    ],
    "ask": [
      "mcp__modelread__estimate_fit",
      "mcp__modelread__compare_hardware",
      "mcp__modelread__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 modelread. Review it before you use it.

Capability tags behind 5 rules
  • mcp__modelread__estimate_fit untrusted-input
  • mcp__modelread__compare_hardware private-data, untrusted-input
  • mcp__modelread__find_models untrusted-input
  • mcp__modelread__ask untrusted-input
  • mcp__modelread__search_models 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.modelread/modelread/verify?hash=4e5f22b781007b158e58ecf7c3ea545c556d518abc1a083523141095631f5374" | jq -e '.changed == false'

Pinned hash 4e5f22b78100, from Nov 18, 2026, 22:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.modelread/modelread/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.modelread/modelread
[![Anlyon Radar](https://radar.anlyon.com/badge/com.modelread/modelread.svg)](https://radar.anlyon.com/servers/com.modelread/modelread)

Source: MCP Registry. Synced Nov 18, 2026, 22:17 UTC.

modelread MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the modelread MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 3 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 modelread MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the modelread 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 modelread MCP server have?

6 tools: 3 write, 3 read. estimate_fit, compare_hardware, ask, find_models, search_models and list_hardware.

Does the modelread MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the modelread MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the modelread MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.