Categories › AI & Agents › Thinking, planning & prompt tools
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Remote server: your requests and data go to mcp.claude-world.com. Claude Code: claude mcp add --transport http ai-worlds-cli-knowledge https://mcp.claude-world.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
worlds_search_knowledge — Search 162 multilingual, source-checked operating manuals for Claude Code, Codex, and Grok Build: 18 CLI usage and feature modules per produworlds_get_document — Read the bounded public excerpt and metadata for one source-checked CLI manual returned by worlds_search_knowledge. Follow canonical_url forworlds_compare_cli_workflows — Find evidence for the same task across Claude Code, Codex, and Grok Build without pretending their commands or authority models are identicaworlds_list_catalog — Return public corpus counts, supported worlds, languages, products, source-quality counts, the build commit, and the current publication gatworlds_search_cli_reference — Search current command paths, flags, interactive commands, configuration names, environment-variable names, workflows, and release drift forworlds_get_cli_command — Return one current command path with all captured flags, arguments, value shapes, availability, risk, release metadata, and official source worlds_get_cli_configuration — Search configuration keys and environment-variable names for one CLI. Returns public schema metadata and source links, never local values.worlds_get_cli_workflow — Find one provider-specific workflow and its recorded command steps without translating flags between providers.worlds_list_cli_versions — Return the exact release snapshot, capture date, factual entity counts, official sources, generated website reference, and drift status for worlds_list_cli_models — Return dated, source-grounded model catalogs for Claude Code, Codex, and Grok Build, including selector syntax, per-model effort support, avworlds_plan_cli_work — Create a read-only, dependency-aware work plan across Claude Code, Codex, and Grok Build. It selects a concrete dated-catalog model and suppworlds_advise_hard_problem — 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 Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.