Skip to content

AI Worlds CLI Knowledge MCP server

com.claude-world/worlds-knowledgeclaude-world.comstreamable-httpv0.6.0Scanned

Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.

12 tools: 3 change things and 9 only read.

Tools: 0 delete, 0 irreversible, 3 write, 9 read.
  • Reads private data · 2
  • Reads text others write · 1
  • Can send data out · 0
  • 2 findings

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 AI Worlds CLI Knowledge MCP server can do

The AI Worlds CLI Knowledge MCP server is published by claude-world.com, a domain the MCP Registry verified. It has 12 tools. It can create or change data (3 tools: worlds_get_cli_command, worlds_plan_cli_work and worlds_advise_hard_problem), but cannot delete data. 9 tools only read.

2 tools read private data (worlds_get_document and worlds_list_catalog); 1 tool brings in text other people can write (worlds_list_cli_versions).

The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 10, 2026, version 0.6.0.

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 3Claude Code: ask
  • worlds_advise_hard_problemChoose the maximum-depth model-and-effort pairing for one difficult problem within the caller's actual CLI set.No 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.
    Description, as the server wrote it
    Choose the maximum-depth model-and-effort pairing for one difficult problem within the caller's actual CLI set. For a single CLI it selects that provider's strongest catalog role; with multiple CLIs it returns provider candidates but does not invent a universal cross-provider winner. It uses single-task depth, never ultra or ultracode orchestration, defaults to read-only, and does not launch a CLI or grant permissions.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_get_cli_commandReturn one current command path with all captured flags, arguments, value shapes, availability, risk, release metadata, and official source links.1 finding

    Why it is in this group

    • The name "worlds_get_cli_command" says "get": a word for reading.
    • The input takes a statement or command to run (input.command), which can change anything it can reach.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "worlds_get_cli_command" 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":false}; The name "worlds_get_cli_command" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Return one current command path with all captured flags, arguments, value shapes, availability, risk, release metadata, and official source links. Accepts a stable id or full command path.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_plan_cli_workCreate a read-only, dependency-aware work plan across Claude Code, Codex, and Grok Build.1 finding

    Why it is in this group

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

    Findings

    • Warn

      The server marks "worlds_plan_cli_work" 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":false}; The description's first verb is "create": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Create a read-only, dependency-aware work plan across Claude Code, Codex, and Grok Build. It selects a concrete dated-catalog model and supported native effort for each workstream, while keeping CLI fit, orchestration, permissions, handoff context, and verification separate. Routing is continuity-first and does not claim benchmark superiority, launch another CLI, or enable permission bypass. Clients that support MCP prompts can enter the same workflow through the `worlds_plan_model_aware_work` prompt (or `worlds_consult_hard_problem` for one hard problem).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 9Show 9 read-only tools
  • worlds_compare_cli_workflowsFind evidence for the same task across Claude Code, Codex, and Grok Build without pretending their commands or authority models are identical.No findings

    Why it is in this group

    • The name "worlds_compare_cli_workflows" says "compare": a word for reading.
    Description, as the server wrote it
    Find evidence for the same task across Claude Code, Codex, and Grok Build without pretending their commands or authority models are identical. Returns separately ranked groups with source dates and canonical links. Best for questions such as configuring MCP, repository instructions, approvals, subagents, or headless CI.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_get_cli_configurationSearch configuration keys and environment-variable names for one CLI.No findings

    Why it is in this group

    • The name "worlds_get_cli_configuration" says "get": a word for reading.
    Description, as the server wrote it
    Search configuration keys and environment-variable names for one CLI. Returns public schema metadata and source links, never local values.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_get_cli_workflowFind one provider-specific workflow and its recorded command steps without translating flags between providers.No findings

    Why it is in this group

    • The name "worlds_get_cli_workflow" says "get": a word for reading.
    Description, as the server wrote it
    Find one provider-specific workflow and its recorded command steps without translating flags between providers.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_get_documentRead the bounded public excerpt and metadata for one source-checked CLI manual returned by worlds_search_knowledge.Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "worlds_get_document" says "get" and "document": it reads documents.
    Description, as the server wrote it
    Read the bounded public excerpt and metadata for one source-checked CLI manual returned by worlds_search_knowledge. Follow canonical_url for the complete manual. Structured CLI command tools remain complete.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_list_catalogReturn public corpus counts, supported worlds, languages, products, source-quality counts, the build commit, and the current publication gate.Reads private dataNo findings

    Why it is in this group

    • The name "worlds_list_catalog" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "return" and "commit": it reads repositories.
    Description, as the server wrote it
    Return public corpus counts, supported worlds, languages, products, source-quality counts, the build commit, and the current publication gate. This public DTO deliberately excludes local paths, package names, and private repository URLs.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_list_cli_modelsReturn dated, source-grounded model catalogs for Claude Code, Codex, and Grok Build, including selector syntax, per-model effort support, availability constraints, and provider-nat…No findings

    Why it is in this group

    • The name "worlds_list_cli_models" says "list": a word for reading.
    Description, as the server wrote it
    Return dated, source-grounded model catalogs for Claude Code, Codex, and Grok Build, including selector syntax, per-model effort support, availability constraints, and provider-native orchestration modes. These are snapshots; verify the live account catalog before launch.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_list_cli_versionsReturn the exact release snapshot, capture date, factual entity counts, official sources, generated website reference, and drift status for all three CLIs.Reads text others writeNo findings

    Why it is in this group

    • The name "worlds_list_cli_versions" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "return" and "website": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Return the exact release snapshot, capture date, factual entity counts, official sources, generated website reference, and drift status for all three CLIs.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_search_cli_referenceSearch current command paths, flags, interactive commands, configuration names, environment-variable names, workflows, and release drift for Claude Code, Codex, and Grok Build.No findings

    Why it is in this group

    • The name "worlds_search_cli_reference" says "search": a word for reading.
    Description, as the server wrote it
    Search current command paths, flags, interactive commands, configuration names, environment-variable names, workflows, and release drift for Claude Code, Codex, and Grok Build. Results contain factual metadata and official source links.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • worlds_search_knowledgeSearch 162 multilingual, source-checked operating manuals for Claude Code, Codex, and Grok Build: 18 CLI usage and feature modules per product in English, Traditional Chinese, and …No findings

    Why it is in this group

    • The name "worlds_search_knowledge" says "search": a word for reading.
    Description, as the server wrote it
    Search 162 multilingual, source-checked operating manuals for Claude Code, Codex, and Grok Build: 18 CLI usage and feature modules per product in English, Traditional Chinese, and Japanese. Website articles, news, newsletters, opinion, and release archives are not in this corpus. Returns bounded excerpts, commands when present, canonical links, official sources, and review dates. It never modifies state.

    Annotations the server declares

    • 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 data2
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:35 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
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://mcp.claude-world.com/mcp: tools/list returned 12 tools to an anonymous client, including worlds_get_cli_command (write), worlds_plan_cli_work (write), worlds_advise_hard_problem (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "worlds_get_cli_command" 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":false}; The name "worlds_get_cli_command" says "get": a word for reading.

    What this check looks for
  • The server marks "worlds_plan_cli_work" 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":false}; The description's first verb is "create": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools3 changed.~3 changedView diff

Install

Pinned to version 0.6.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http worlds-knowledge https://mcp.claude-world.com/mcp
claude mcp add --transport http worlds-knowledge https://mcp.claude-world.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__worlds-knowledge__worlds_search_knowledge",
      "mcp__worlds-knowledge__worlds_get_document",
      "mcp__worlds-knowledge__worlds_compare_cli_workflows",
      "mcp__worlds-knowledge__worlds_list_catalog",
      "mcp__worlds-knowledge__worlds_search_cli_reference",
      "mcp__worlds-knowledge__worlds_get_cli_configuration",
      "mcp__worlds-knowledge__worlds_get_cli_workflow",
      "mcp__worlds-knowledge__worlds_list_cli_versions",
      "mcp__worlds-knowledge__worlds_list_cli_models"
    ],
    "ask": [
      "mcp__worlds-knowledge__worlds_get_cli_command",
      "mcp__worlds-knowledge__worlds_plan_cli_work",
      "mcp__worlds-knowledge__worlds_advise_hard_problem"
    ],
    "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 worlds-knowledge. Review it before you use it.

Capability tags behind 3 rules
  • mcp__worlds-knowledge__worlds_get_document private-data
  • mcp__worlds-knowledge__worlds_list_catalog private-data
  • mcp__worlds-knowledge__worlds_list_cli_versions 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.claude-world/worlds-knowledge/verify?hash=5773a21ecd128c2181dc0f4b382ff52d5f2945acc2871bcc8a67e0da99e2d9f9" | jq -e '.changed == false'

Pinned hash 5773a21ecd12, from Nov 10, 2026, 12:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.claude-world/worlds-knowledge/changes.xml

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

Badge

Anlyon Radar badge for com.claude-world/worlds-knowledge
[![Anlyon Radar](https://radar.anlyon.com/badge/com.claude-world/worlds-knowledge.svg)](https://radar.anlyon.com/servers/com.claude-world/worlds-knowledge)

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:53 UTC.

AI Worlds CLI Knowledge MCP server: questions and answers

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

Is the AI Worlds CLI Knowledge MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 3 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the AI Worlds CLI Knowledge MCP server delete data?

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

Can the AI Worlds CLI Knowledge 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 AI Worlds CLI Knowledge MCP server have?

12 tools: 3 write, 9 read. worlds_get_cli_command, worlds_plan_cli_work, worlds_advise_hard_problem, worlds_search_knowledge, worlds_get_document, worlds_compare_cli_workflows, worlds_list_catalog, worlds_search_cli_reference and 4 more.

Does the AI Worlds CLI Knowledge MCP server need sign-in or OAuth?

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

Does the AI Worlds CLI Knowledge MCP server send data to outside services?

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

Has the AI Worlds CLI Knowledge MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.