Laplace’s Mini World MCP server
io.github.Keith-CY/laplace-mini-world-mcpKeith-CYstreamable-httpv1.0.1Scanned
Interactive 3D science models in Chinese and English, found and shown live in the chat.
3 tools: 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
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 Laplace’s Mini World MCP server can do
The Laplace’s Mini World MCP server is published by the GitHub account Keith-CY. It has 3 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (show_model); 1 tool brings in text other people can write (show_model).
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 15, 2026, version 1.0.1.
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.
3 tools
Only reads 3Show 3 read-only tools
list_chaptersLists one plate’s chapters (ids and titles) and the lab settings it accepts (ids, ranges, options), for show_model.No findings
Why it is in this group
- The name "list_chapters" says "list": a word for reading.
Description, as the server wrote it Lists one plate’s chapters (ids and titles) and the lab settings it accepts (ids, ranges, options), for show_model. Use it when the user wants another part of a plate than the one search_models gave, or wants to set the lab.
Annotations the server declares
- title: List a model’s chapters
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_modelsUse this when the user asks how something works or why something happens in physics, engineering, AI, biology and medicine, earth and space science or mathematics, or asks to see o…No findings
Why it is in this group
- The name "search_models" says "search": a word for reading.
Description, as the server wrote it Use this when the user asks how something works or why something happens in physics, engineering, AI, biology and medicine, earth and space science or mathematics, or asks to see or try a mechanism: e.g. “why do we have seasons”, “how does a jet engine work”, “潮汐是怎么形成的”, “Transformer 的注意力是什么”. Searches the interactive 3D models (“plates”) on world.lapla.si: first an index of the questions each plate answers (Chinese and English), then titles and topics. Returns the best plates, each with its slug, the chapter that answers the question and sometimes lab settings, to pass to show_model. Returns no results when no plate covers the question. Not for news, prices, homework calculations, or medical, legal or financial advice.
Annotations the server declares
- title: Find a science model
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
show_modelShows one interactive 3D model from world.lapla.si in the conversation, opening at the chapter that answers the user’s question; the user can turn it, step through its chapters and…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "show_model" says "show": a word for reading.
What it can reach
- private-dataThe description's first sentence says "show" and "conversation": it reads messages.
- untrusted-inputThe description's first sentence says "show" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it Shows one interactive 3D model from world.lapla.si in the conversation, opening at the chapter that answers the user’s question; the user can turn it, step through its chapters and try its lab. Use it after search_models with the slug and chapter (and params) it returned, or when the user names a plate. Also returns a short text summary and the plate’s link, for clients that show no UI.
Annotations the server declares
- title: Show a live 3D model
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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 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.
Tools1 changed.~1 changedView diff
- Changed:show_modelOnly readsinputSchema
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http laplace-mini-world https://world.lapla.si/mcpclaude mcp add --transport http laplace-mini-world https://world.lapla.si/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__laplace-mini-world__search_models",
"mcp__laplace-mini-world__show_model",
"mcp__laplace-mini-world__list_chapters"
],
"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 laplace-mini-world. Review it before you use it.
Capability tags behind 1 rule
- mcp__laplace-mini-world__show_model 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/io.github.Keith-CY/laplace-mini-world-mcp/verify?hash=54703b02e659f0a3703d2ca6946b8ece7dfd902a48ec0ad10ab49c2c1abe7109" | jq -e '.changed == false'Pinned hash 54703b02e659, from Nov 15, 2026, 23:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Keith-CY/laplace-mini-world-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Keith-CY/laplace-mini-world-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:17 UTC.
Laplace’s Mini World MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Laplace’s Mini World 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 Laplace’s Mini World MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Laplace’s Mini World 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 Laplace’s Mini World MCP server have?
- 3 tools: 3 read. search_models, show_model and list_chapters.
Does the Laplace’s Mini World MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Laplace’s Mini World MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Laplace’s Mini World MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 2, 2026. Every change is on this page and in its Atom feed.