AI Worlds CLI Knowledge

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AI Worlds CLI Knowledge": {
      "url": "https://mcp.claude-world.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (12)

• worlds_search_knowledge read-only

  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.

  Parameters:

  • query (required) — string — Natural-language task, concept, error, or exact CLI command.
  • limit — integer
  • scope — string — The only collection is core: balanced, source-checked CLI usage and feature manuals.
  • offset — integer
  • worlds — array — Optional canonical world filters: claude, gpt, or grok.
  • products — array — Optional product filters such as claude-code, codex, or grok-build.
  • languages — array — Optional locale filters: en, zh-tw, or ja.
  • content_types — array — Optional content filters, for example tutorial or field-guide.
  • source_status — array — Optional provenance filter. Every published manual is source-checked.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_get_document read-only

  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.

  Parameters:

  • id (required) — string — Stable document id from a search or comparison result.
  • offset — integer
  • max_characters — integer

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_compare_cli_workflows read-only

  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.

  Parameters:

  • query (required) — string
  • language — string
  • products — array
  • limit_per_product — integer

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_list_catalog read-only

  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.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_search_cli_reference read-only

  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.

  Parameters:

  • query (required) — string
  • kinds — array
  • limit — integer
  • offset — integer
  • products — array
  • availability — array

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_get_cli_command read-only

  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.

  Parameters:

  • product (required) — string
  • command (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_get_cli_configuration read-only

  Search configuration keys and environment-variable names for one CLI. Returns public schema metadata and source links, never local values.

  Parameters:

  • product (required) — string
  • limit — integer
  • query — string
  • offset — integer
  • include — string
  • availability — array

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_get_cli_workflow read-only

  Find one provider-specific workflow and its recorded command steps without translating flags between providers.

  Parameters:

  • product (required) — string
  • workflow (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_list_cli_versions read-only

  Return the exact release snapshot, capture date, factual entity counts, official sources, generated website reference, and drift status for all three CLIs.

  Parameters:

  • products — array

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_list_cli_models read-only

  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.

  Parameters:

  • products — array

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_plan_cli_work read-only

  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.

  Parameters:

  • task (required) — string
  • current_cli (required) — string — CLI holding the active conversation; continuity is preferred unless switching has a concrete benefit.
  • strategy — string
  • workstreams — array
  • available_clis — array
  • risk_tolerance — string
  • orchestration_mode — string
  • max_parallel_tracks — integer
  • execution_environment — string
  • require_independent_review — boolean

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• worlds_advise_hard_problem read-only

  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.

  Parameters:

  • task (required) — string
  • current_cli (required) — string
  • preferred_cli — string — Optional user-selected provider. This is an explicit preference, not a benchmark verdict.
  • available_clis — array
  • selection_scope — string
  • execution_intent — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.