# AI Worlds CLI Knowledge MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/com-claude-world-worlds-knowledge
- Repository: https://github.com/claude-world/claude-world.com
- Website: https://claude-world.com/mcp/

## Install
- Endpoint: https://mcp.claude-world.com/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://mcp.claude-world.com/mcp

## Tools
- worlds_search_knowledge (Search AI Worlds Knowledge) - 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. Endpoint: https://mcp.claude-world.com/mcp
- worlds_get_document (Read a Knowledge Document) - 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. Endpoint: https://mcp.claude-world.com/mcp
- worlds_compare_cli_workflows (Compare Coding-Agent Workflows) - 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. Endpoint: https://mcp.claude-world.com/mcp
- worlds_list_catalog (List Knowledge Catalog Status) - 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. Endpoint: https://mcp.claude-world.com/mcp
- worlds_search_cli_reference (Search Current CLI Reference) - 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. Endpoint: https://mcp.claude-world.com/mcp
- worlds_get_cli_command (Get One CLI Command) - 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. Endpoint: https://mcp.claude-world.com/mcp
- worlds_get_cli_configuration (Find CLI Configuration) - Search configuration keys and environment-variable names for one CLI. Returns public schema metadata and source links, never local values. Endpoint: https://mcp.claude-world.com/mcp
- worlds_get_cli_workflow (Get a CLI Workflow) - Find one provider-specific workflow and its recorded command steps without translating flags between providers. Endpoint: https://mcp.claude-world.com/mcp
- worlds_list_cli_versions (List CLI Versions and Coverage) - Return the exact release snapshot, capture date, factual entity counts, official sources, generated website reference, and drift status for all three CLIs. Endpoint: https://mcp.claude-world.com/mcp
- worlds_list_cli_models (List CLI Models and Effort Support) - 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. Endpoint: https://mcp.claude-world.com/mcp
- worlds_plan_cli_work (Plan Model-Aware 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 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. Endpoint: https://mcp.claude-world.com/mcp
- worlds_advise_hard_problem (Consult the Strongest Available Model for One 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 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. Endpoint: https://mcp.claude-world.com/mcp

## Resources
- worlds://catalog - AI Worlds Knowledge Catalog Public corpus inventory without control-plane paths or private build metadata. MIME type: application/json

## Prompts
- worlds_plan_model_aware_work - Plan Work by CLI, Model, and Effort Enter a planning mode that decomposes work, preserves continuity, and routes bounded workstreams by documented CLI and model fit while keeping native effort, provider orchestration, permissions, and verification separate. Arguments: task, current_cli, language
- worlds_consult_hard_problem - Consult a Maximum-Depth Model for One Hard Problem Use the Worlds Knowledge MCP as a model-selection consultant for one difficult problem, including single-CLI users, without enabling orchestration or expanding authority. Arguments: task, current_cli, language
- worlds_research_cli_workflow - Research a Coding-Agent Workflow Create a retrieval-first prompt for answering a Claude Code, Codex, or Grok Build operating question with dated evidence. Arguments: task, language

## Metadata
- Owner: com.claude-world
- Version: 0.5.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Aug 3, 2026
- Source: https://registry.modelcontextprotocol.io