Skip to content

Hologram Model Hub MCP server

foundation.uor.hub/model-hubhub.uor.foundationstreamable-httpv1.0.0Scanned

Find open models and get download links with the SHA-256 each file must have.

3 tools: 3 only read.

Tools: 0 delete, 0 irreversible, 0 write, 3 read.
  • Reads private data · 2
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Sign-in required, no OAuth metadata. 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.
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 Hologram Model Hub MCP server can do

The Hologram Model Hub MCP server is published by hub.uor.foundation, a domain the MCP Registry verified. It has 3 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

2 tools read private data (get_model and resolve_file).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Last scanned Nov 11, 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.

3 tools

Only reads 3Show 3 read-only tools
  • get_modelThe pinned revision of one model, its files with size and SHA-256, its GGUF quantisations if any, and its sources with their current health.Reads private dataNo findings

    Why it is in this group

    • The name "get_model" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    Description, as the server wrote it
    The pinned revision of one model, its files with size and SHA-256, its GGUF quantisations if any, and its sources with their current health.
  • resolve_fileWhere to download one file of a model right now, the SHA-256 it must have, how to check it, and the commands that hand it to an engine (hf, Ollama, llama.cpp).Reads private dataNo findings

    Why it is in this group

    • The name "resolve_file" says "resolve": a word for reading.

    What it can reach

    • private-dataThe name "resolve_file" says "resolve" and "file": it reads files.
    • private-dataThe description's first sentence says "file": it reads files.
    Description, as the server wrote it
    Where to download one file of a model right now, the SHA-256 it must have, how to check it, and the commands that hand it to an engine (hf, Ollama, llama.cpp). Give either a path or, for GGUF models, a quantisation such as Q4_K_M.
  • search_modelsFind open models in the hub's index.No findings

    Why it is in this group

    • The name "search_models" says "search": a word for reading.
    Description, as the server wrote it
    Find open models in the hub's index. Every result has all of its files addressed by SHA-256. Returns id, task, library, licence, parameters, weight size, downloads and where the bytes live.

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 untrusted-input or outbound.

Reads private data2
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.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 18:54 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
405
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: initialize answered HTTP 405.

Posture changes

  1. Nov 20, 2026
    • HTTP status of an anonymous initialize: 200 to 405
    • tools/list served without credentials: yes to no
    • 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.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 405; tools/list served without credentials: yes -> no; Protocol version: 2025-06-18 -> none.View diff
    • HTTP status of an anonymous initialize: 200 to 405
    • tools/list served without credentials: yes to no
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http model-hub https://hub.uor.foundation/mcp
claude mcp add --transport http model-hub https://hub.uor.foundation/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__model-hub__search_models",
      "mcp__model-hub__get_model",
      "mcp__model-hub__resolve_file"
    ],
    "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 model-hub. Review it before you use it.

Capability tags behind 2 rules
  • mcp__model-hub__get_model private-data
  • mcp__model-hub__resolve_file private-data

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/foundation.uor.hub/model-hub/verify?hash=b837ee3fdc25d64b88100dd52d5bbc50b22e2f668b0cc3385fa0dd88c7636801" | jq -e '.changed == false'

Pinned hash b837ee3fdc25, from Nov 11, 2026, 13:17 UTC.

Watch

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

https://radar.anlyon.com/servers/foundation.uor.hub/model-hub/changes.xml

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

Badge

Anlyon Radar badge for foundation.uor.hub/model-hub
[![Anlyon Radar](https://radar.anlyon.com/badge/foundation.uor.hub/model-hub.svg)](https://radar.anlyon.com/servers/foundation.uor.hub/model-hub)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:12 UTC.

Hologram Model Hub MCP server: questions and answers

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

Is the Hologram Model Hub MCP server safe?

No scan can promise that. What its definitions show: 3 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 Hologram Model Hub MCP server delete data?

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

Can the Hologram Model Hub 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 Hologram Model Hub MCP server have?

3 tools: 3 read. search_models, get_model and resolve_file.

Does the Hologram Model Hub MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Hologram Model Hub MCP server send data to outside services?

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

Has the Hologram Model Hub MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.