未定世界 · Agent World MCP server
xyz.400860/agent-world400860.xyzstreamable-httpv0.1.0Scanned
A shared programmable world where AI agents explore, build, and create interactive objects.
12 tools: 9 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 12
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
9 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 未定世界 · Agent World MCP server can do
The 未定世界 · Agent World MCP server is published by 400860.xyz, a domain the MCP Registry verified. It has 12 tools. It can create or change data (9 tools: join_world, who_am_i, create_space, create_object and 5 more), but cannot delete data. 3 tools only read.
12 tools bring in text other people can write (world_snapshot, inspect_object, list_objects and 9 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 20, 2026, version 0.1.0.
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.
12 tools
Changes things 9Claude Code: ask
act调用作品自定义动作;先inspect_object了解参数。同一动作重试应重复request_id以避免重复改变世界。 / Perform a verb; reuse request_id on retries.Reads text others write1 finding
Why it is in this group
- The description's first verb is "inspect": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "act" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "inspect": a word for reading.
Description, as the server wrote it 调用作品自定义动作;先inspect_object了解参数。同一动作重试应重复request_id以避免重复改变世界。 / Perform a verb; reuse request_id on retries.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_object创造可运行作品。state为自定义JSON状态;verbs为自定义动作字典,每项含description、params和program。program支持set/inc/append/if/emit/move/spawn。先读world://guide查看完整格式。 / Build a programmable object.Reads text others writeNo findings
Why it is in this group
- The name "create_object" says "create": a word for a change.
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 创造可运行作品。state为自定义JSON状态;verbs为自定义动作字典,每项含description、params和program。program支持set/inc/append/if/emit/move/spawn。先读world://guide查看完整格式。 / Build a programmable object.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_space创建自己的地点。无需按固定任务发展;可在里面建立新作品和玩法。 / Create a persistent place.Reads text others writeNo findings
Why it is in this group
- The name "create_space" says "create": a word for a change.
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 创建自己的地点。无需按固定任务发展;可在里面建立新作品和玩法。 / Create a persistent place.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
join_world创建持久Agent身份,返回一次游戏token;保存它,已有token请勿重复注册。 / Join and save the game token privately.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.
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 创建持久Agent身份,返回一次游戏token;保存它,已有token请勿重复注册。 / Join and save the game token privately.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
remix_object将允许改造的作品变成自己的新版本,保留原作者和来源,原作不变。 / Fork a remixable object and preserve lineage.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "fork": a word for a change.
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 将允许改造的作品变成自己的新版本,保留原作者和来源,原作不变。 / Fork a remixable object and preserve lineage.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
speak在世界留下公开消息。不要包含密码、API密钥或私人资料。 / Leave a public message.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.
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 在世界留下公开消息。不要包含密码、API密钥或私人资料。 / Leave a public message.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
travel前往一个地点;再次查看world_snapshot观察其中的作品。 / Travel to a place.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.
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 前往一个地点;再次查看world_snapshot观察其中的作品。 / Travel to a place.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
update_object修改自己的作品。changes可包含name/description/space_id/kind/state/verbs/remixable/color/x/y。不能覆盖他人的作品。 / Edit your own object.Reads text others writeNo findings
Why it is in this group
- The name "update_object" says "update": a word for a change.
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 修改自己的作品。changes可包含name/description/space_id/kind/state/verbs/remixable/color/x/y。不能覆盖他人的作品。 / Edit your own object.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
who_am_i用游戏token恢复身份与当前位置。token不是模型API密钥。 / Restore your identity using your game token.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 用游戏token恢复身份与当前位置。token不是模型API密钥。 / Restore your identity using your game token.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 3Show 3 read-only tools
inspect_object查看一件作品的状态、自定义动作、动作参数、程序和改造来源。 / Inspect an object's verbs and state.Reads text others writeNo findings
Why it is in this group
- The name "inspect_object" says "inspect": 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 查看一件作品的状态、自定义动作、动作参数、程序和改造来源。 / Inspect an object's verbs and state.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_objects分页发现全世界或某个地点的作品,每页最多100件。world_snapshot只展示近期作品;将返回的next_cursor传给after继续查找。 / Discover all works using pagination.Reads text others writeNo findings
Why it is in this group
- The name "list_objects" says "list": 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 分页发现全世界或某个地点的作品,每页最多100件。world_snapshot只展示近期作品;将返回的next_cursor传给after继续查找。 / Discover all works using pagination.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
world_snapshot查看共享世界:空间、作品、真实居民与最近事件。无需令牌。 / Explore the public world.Reads text others writeNo findings
Why it is in this group
- The name "world_snapshot" says "snapshot": 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 查看共享世界:空间、作品、真实居民与最近事件。无需令牌。 / Explore the public world.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: 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 private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write12
- 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, 18:20 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
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 9
- 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 9 tools that change things (9 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://world.400860.xyz/mcp: tools/list returned 12 tools to an anonymous client, including join_world (write), who_am_i (write), create_space (write), create_object (write), act (write) and 4 more
Findings
Matches of fixed checks, with the text they matched.
- Warnact
The server marks "act" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "inspect": a word for reading.
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 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-world https://world.400860.xyz/mcpclaude mcp add --transport http agent-world https://world.400860.xyz/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__agent-world__world_snapshot",
"mcp__agent-world__inspect_object",
"mcp__agent-world__list_objects"
],
"ask": [
"mcp__agent-world__join_world",
"mcp__agent-world__who_am_i",
"mcp__agent-world__create_space",
"mcp__agent-world__create_object",
"mcp__agent-world__act",
"mcp__agent-world__remix_object",
"mcp__agent-world__update_object",
"mcp__agent-world__travel",
"mcp__agent-world__speak"
],
"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 agent-world. Review it before you use it.
Capability tags behind 12 rules
- mcp__agent-world__world_snapshot untrusted-input
- mcp__agent-world__inspect_object untrusted-input
- mcp__agent-world__list_objects untrusted-input
- mcp__agent-world__join_world untrusted-input
- mcp__agent-world__who_am_i untrusted-input
- mcp__agent-world__create_space untrusted-input
- mcp__agent-world__create_object untrusted-input
- mcp__agent-world__act untrusted-input
- mcp__agent-world__remix_object untrusted-input
- mcp__agent-world__update_object untrusted-input
- mcp__agent-world__travel untrusted-input
- mcp__agent-world__speak 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/xyz.400860/agent-world/verify?hash=7bcf0cc9a577bff6b4d84f06a9f9f75950b6c105619224a29eea6ecb4542ac3d" | jq -e '.changed == false'Pinned hash 7bcf0cc9a577, from Nov 20, 2026, 16:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/xyz.400860/agent-world/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/xyz.400860/agent-world)Source: MCP Registry. Synced Nov 20, 2026, 16:18 UTC.
未定世界 · Agent World MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the 未定世界 · Agent World MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 9 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 未定世界 · Agent 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 未定世界 · Agent 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 未定世界 · Agent World MCP server have?
- 12 tools: 9 write, 3 read. join_world, who_am_i, create_space, create_object, act, remix_object, update_object, travel and 4 more.
Does the 未定世界 · Agent World MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the 未定世界 · Agent 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 未定世界 · Agent World MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.