Skip to content

InkRoom MCP server

io.github.InkRoomAI/inkroomInkRoomAIstreamable-httpv0.3.23Scanned

Generate, edit and upscale images with references, batch jobs, cost previews and original downloads.

3 tools: 3 only read.

Tools: 0 delete, 0 irreversible, 0 write, 3 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.
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 InkRoom MCP server can do

The InkRoom MCP server is published by the GitHub account InkRoomAI. It has 3 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, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 16, 2026, version 0.3.23.

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
  • helpRead static help without an MCP Token, model call or credit charge.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read static help without an MCP Token, model call or credit charge. All help topics are available. Returns topic, steps, examples, documentation/setup links and versions. Account, billing and generation topics describe authenticated operations; they do not read personal data or execute work. Anonymous execution is limited to list_models, help and public prompts.

    Annotations the server declares

    • idempotentHint: true
    • readOnlyHint: true
    • title: Help | Capabilities and usage
  • list_modelsRead the public image-model catalog.No findings

    Why it is in this group

    • The name "list_models" says "list": a word for reading.
    Description, as the server wrote it
    Read the public image-model catalog. Returns scope, accountAuthorization=not_evaluated, models (id, status=listed, offers with parameters and public credit prices), pricingSource and visibleCount. priceSemantics=public_sale_exact; prices retain three decimals, free offers are zero and missing pricing is explicit. Listed configuration does not guarantee account access or capacity, and generation preview confirms the final charge. The full toolset requires your valid MCP Token.

    Annotations the server declares

    • idempotentHint: true
    • readOnlyHint: true
    • title: Models | Image models and pricing
  • promptsRead public prompts without an MCP Token, model call or credit charge.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read public prompts without an MCP Token, model call or credit charge. search (default) queries published, reviewed system recommendations; get reads a currently public detail by the id returned from search. scope must be omitted or recommended; mine, favorites and private data remain authenticated. Returns scope, accountAuthorization=not_evaluated, action and list (items/pagination) or item (original text/public link). Never generates, syncs, evaluates or rewrites prompts.

    Annotations the server declares

    • idempotentHint: true
    • readOnlyHint: true
    • title: Prompts | Case library

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:58 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.

  1. Tools1 changed.~1 changedView diff

Install

Pinned to version 0.3.23. Values in angle brackets are yours to fill in.

claude mcp add --transport http inkroom https://mcp.inkroom.ai --header 'Authorization: <your-authorization>'
claude mcp add --transport http inkroom https://mcp.inkroom.ai --header 'Authorization: <your-authorization>'

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__inkroom__help",
      "mcp__inkroom__list_models",
      "mcp__inkroom__prompts"
    ],
    "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 inkroom. 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/io.github.InkRoomAI/inkroom/verify?hash=a5b5758d88964d0feb2d232857ecbd35844a61c675afc669388fb747bc791fdf" | jq -e '.changed == false'

Pinned hash a5b5758d8896, from Nov 16, 2026, 17:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.InkRoomAI/inkroom/changes.xml

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

Badge

Anlyon Radar badge for io.github.InkRoomAI/inkroom
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.InkRoomAI/inkroom.svg)](https://radar.anlyon.com/servers/io.github.InkRoomAI/inkroom)

Source: MCP Registry. Synced Oct 21, 2026, 18:16 UTC.

InkRoom MCP server: questions and answers

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

Is the InkRoom 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 InkRoom MCP server delete data?

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

Can the InkRoom 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 InkRoom MCP server have?

3 tools: 3 read. help, list_models and prompts.

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

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

Does the InkRoom MCP server send data to outside services?

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

Has the InkRoom MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 3, 2026. Every change is on this page and in its Atom feed.