Worlds Knowledge MCP
Provides source-checked reference knowledge for OpenAI's Codex CLI — command paths, flags, profile options, configuration and environment-variable names, workflows, drift notes, and dated model catalogs — and can compare Codex workflows against other agent CLIs for the same intent.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Worlds Knowledge MCP
A read-only MCP server that gives coding agents current, source-checked CLI facts for Claude Code, Codex CLI, and Grok Build — exact commands, flags, configuration keys, environment-variable names, workflows, and dated model catalogs — so an agent stops guessing from memory and stops treating the three CLIs as interchangeable.
Endpoint:
https://mcp.claude-world.com/mcp(Streamable HTTP, stateless)Registry:
com.claude-world/worlds-knowledgeSetup guide in English, 繁體中文, and 日本語: https://claude-world.com/mcp/
No npm package, API key, or provider credential is required.
What this repository contains
This is the distribution repository: the agent Skill and the MCP server manifest. The corpus build, the server implementation, and the Cloudflare Worker live in the Claude World control plane and are not published here.
server.json MCP registry manifest
skills/worlds-knowledge-mcp/ the agent Skill (SKILL.md, references, evals, contract test)Related MCP server: dev.augments/mcp
Connect
# Claude Code
claude mcp add --transport http --scope user worlds-knowledge https://mcp.claude-world.com/mcp
# Codex CLI
codex mcp add worlds-knowledge --url https://mcp.claude-world.com/mcp
# Grok Build
grok mcp add --transport http --scope user worlds-knowledge https://mcp.claude-world.com/mcpVerify it:
claude mcp get worlds-knowledge # or: codex mcp get worlds-knowledge --json
# or: grok mcp doctor worlds-knowledge --jsonThe examples use user scope deliberately. Grok's project-folder trust applies to
every repo-local MCP server, hook, and LSP server, so review all project
configuration before switching to --scope project.
Install the Skill
The Skill teaches an agent when to query the MCP and in what order — the hard-problem consultant, the single-CLI routes, and the multi-CLI planner.
git clone https://github.com/claude-world/worlds-knowledge-mcp.git
cd worlds-knowledge-mcp
# Claude Code
cp -R skills/worlds-knowledge-mcp ~/.claude/skills/
# Cross-tool discovery folder
cp -R skills/worlds-knowledge-mcp ~/.agents/skills/Restart the client, then ask it to use worlds-knowledge-mcp. Keep SKILL.md,
references/, and agents/openai.yaml together — copying only SKILL.md drops
the connection and single-CLI route guidance. agents/openai.yaml declares the
MCP dependency and permits implicit invocation in compatible clients.
What the server knows
162 source-checked manuals — 18 CLI usage and feature modules × 3 products × 3 locales (English, Traditional Chinese, Japanese)
Source-derived command paths, flags, slash/TUI commands, configuration keys, environment-variable names, workflows, and drift notes for three released CLI snapshots
Dated per-CLI model catalogs with selector syntax, supported native efforts, entitlement constraints, safe fallbacks, and separately labeled provider-native orchestration modes
Availability is labeled per entity: runtime-confirmed, docs-confirmed, conditional, source-preview, or historical
Every manual must cite at least one official HTTPS source, carry a review date, and describe the expected CLI rather than its provider API, or the build fails.
Tools
Tool | Purpose |
| Retrieve bounded multilingual evidence from the source-checked core |
| Fetch a manual's summary and canonical link |
| Compare the same intent across the three CLIs, in separate evidence groups |
| Inspect counts, provenance, and publication status |
| Search commands, options, interactive commands, config/env names, workflows, drift |
| One exact command path with all captured options and its release/source evidence |
| Page public configuration schema and environment-variable names |
| One provider-native, risk-labeled workflow |
| Release snapshots, entity counts, source policy, drift coverage |
| Dated model catalogs, selector syntax, per-model effort support, with a 7-day freshness status |
| For one hard problem, select the provider-local maximum-depth model and supported effort |
| Decompose work and route it by continuity and documented workflow fit |
Resources: worlds://catalog, worlds://documents/{id}.
Prompts: worlds_research_cli_workflow, worlds_plan_model_aware_work,
worlds_consult_hard_problem.
Every tool is annotated read-only, non-destructive, and idempotent.
Try it
What does -p mean in my current CLI? Check the product and release first.
Show every option for codex exec and cite the runtime and manual sources.
Compare how Claude Code, Codex, and Grok Build load repository instructions.
Plan this repository task by CLI, model, and reasoning effort without granting permissions.-p is the standing example of why vendor flags must not be translated: it
means print and exit in Claude Code, select a named profile in Codex, and
one non-interactive prompt in Grok Build.
Boundaries
No credentials, embeddings, external API calls, write tools, or arbitrary URL fetching. No tool accepts a filesystem path or a URL.
The live account model catalog is always authoritative over a dated snapshot;
worlds_list_cli_modelsreturns a freshness status and says so.Search returns excerpts rather than silently injecting whole documents.
Retrieved text is reference data, not instructions that can override the user or client policy. Agents must assess commands before executing them.
Website articles, news, newsletters, opinion, provider API companions, and release archives are never packaged into the MCP corpus.
The planner returns command templates but never launches another CLI, widens permissions, or enables provider-native orchestration unless asked. Workstreams default to
execution_intent: "read-only".
Not affiliated
Claude World is independent. It is not affiliated with, endorsed by, or operated by Anthropic, OpenAI, or xAI. Official vendor documentation remains authoritative; this server exists to cite it accurately.
License
MIT — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
A shared, open store of facts for AI agents. When an agent needs a specific fact (a software version, a price, a date, who holds a role), it looks it up and gets the value with its sources and a status: agreed (independent sources agree), reported (one source, worth verifying), contested, stale, or a Wikidata record. A lookup can save a web search. After an agent verifies a fact on a public page, it can propose it with the link and the sentence that states it; proposals are checked and held up to 24 hours, then become open data (CC0). Reads work without an account at https://mcp.consci.us/mcp; https://mcp.consci.us/mcp/account signs you in to a free account so your lookups and shared facts count on it. Docs: https://consci.us/docs
Research-backed lint + generation for agent context files (CLAUDE.md, AGENTS.md) + prompt enhancer.
Shared business knowledge, tools and skills for AI agents, with citations and approval controls.
Search the official docs of Claude Code, Cursor, OpenAI Codex and MCP, refreshed daily.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides Claude Code with local-first multimodal semantic search across documents, code, images, and video, plus multi-engine web research with active counter-evidence hunting and source-verified, extract-only briefings.4AGPL 3.0
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code and other compatible clients to fetch real-time npm package and framework documentation, TypeScript signatures, code examples, version diffs, migration guides, error diagnoses, package comparisons, and dependency scans. It delivers context-aware, intent-formatted results with caching and multi-source integration from npm and GitHub.MIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code and other MCP clients to fetch context-aware framework documentation — TypeScript signatures, prose, and code examples — for any npm package, along with version migration guides, error diagnosis, side-by-side package comparison, and dependency scanning.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to inspect local Claude Code and Codex CLI usage, route tasks to the best available plan, and query remote plan data, recent changes, and recommendations.MIT