# AI Worlds CLI Knowledge (remote · mcp.claude-world.com)

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

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.claude-world.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/com-claude-world-worlds-knowledge/mcp.md), [page](https://verifymcp.io/servers/com-claude-world-worlds-knowledge/mcp)

## Channel facts

- Endpoint: `https://mcp.claude-world.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.5.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 1450 tokens (~111/item across 13 items; 12 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 77/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 20% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### Claude

```bash
claude mcp add --transport http com-claude-world-worlds-knowledge https://mcp.claude-world.com/mcp
```

### Codex

```toml
[mcp_servers.com-claude-world-worlds-knowledge]
url = "https://mcp.claude-world.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-claude-world-worlds-knowledge": {
      "type": "remote",
      "url": "https://mcp.claude-world.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-claude-world-worlds-knowledge --url https://mcp.claude-world.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-claude-world-worlds-knowledge:
    url: "https://mcp.claude-world.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-claude-world-worlds-knowledge": {
      "type": "http",
      "url": "https://mcp.claude-world.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 70, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “worlds_get_document” rewrote its description, which is the text the model reads
- [security] Tool “worlds_search_knowledge” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional] New prompt “worlds_consult_hard_problem”
- [functional] New prompt “worlds_plan_model_aware_work”
- [functional] Server version: 0.3.0 → 0.5.0
- [functional] New tool “worlds_advise_hard_problem”
- [functional] New tool “worlds_list_cli_models”
- [functional] New tool “worlds_plan_cli_work”
- [cosmetic] “worlds_search_knowledge” reworded the description of “scope”
- [cosmetic] “worlds_search_knowledge” reworded the description of “source_status”

### 2026-08-02 (score 69, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-01 (score 69)

First indexed and scored.

## MCP tools (12)

### `worlds_search_knowledge` (~247 tokens)

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.

Input parameters:

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

Output parameters:

- `count` (number)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `offset` (number)
- `query` (string)
- `scope` (string)
- `total` (number)

### `worlds_get_document` (~77 tokens)

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.

Input parameters:

- `id` (string, required): Stable document id from a search or comparison result.
- `max_characters` (integer)
- `offset` (integer)

Output parameters:

- `canonical_url` (string)
- `content_type` (string)
- `fixed_excerpt` (string)
- `id` (string)
- `knowledge_collection` (string)
- `language` (string)
- `official_sources` (array)
- `product` (string)
- `published_at` (string)
- `reviewed_at` (string)
- `rights_basis` (string)
- `source_status` (string)
- `summary` (string)
- `title` (string)
- `world` (string)

### `worlds_compare_cli_workflows` (~100 tokens)

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.

Input parameters:

- `language` (string)
- `limit_per_product` (integer)
- `products` (array)
- `query` (string, required)

Output parameters:

- `groups` (array)
- `language` (string)
- `query` (string)

### `worlds_list_catalog` (~51 tokens)

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.

Output parameters:

- `content_policy` (string)
- `dataset_version` (string)
- `generated_at` (string)
- `released_at` (string)
- `schema_version` (number)
- `total_documents` (number)
- `worlds` (array)

### `worlds_search_cli_reference` (~95 tokens)

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.

Input parameters:

- `availability` (array)
- `kinds` (array)
- `limit` (integer)
- `offset` (integer)
- `products` (array)
- `query` (string, required)

Output parameters:

- `count` (number)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `offset` (number)
- `query` (string)
- `total` (number)

### `worlds_get_cli_command` (~61 tokens)

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.

Input parameters:

- `command` (string, required)
- `product` (string, required)

Output parameters:

- `command` (object)
- `display_name` (string)
- `product` (string)
- `reference_url` (string)
- `release` (object)
- `sources` (array)

### `worlds_get_cli_configuration` (~75 tokens)

Find CLI Configuration

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

Input parameters:

- `availability` (array)
- `include` (string)
- `limit` (integer)
- `offset` (integer)
- `product` (string, required)
- `query` (string)

Output parameters:

- `count` (number)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `offset` (number)
- `product` (string)
- `query` (string)
- `reference_url` (string)
- `release_version` (string)
- `total` (number)

### `worlds_get_cli_workflow` (~41 tokens)

Get a CLI Workflow

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

Input parameters:

- `product` (string, required)
- `workflow` (string, required)

Output parameters:

- `commands` (array)
- `guide_url` (string)
- `interactive_commands` (array)
- `product` (string)
- `reference_url` (string)
- `release_version` (string)
- `sources` (array)
- `workflow` (object)

### `worlds_list_cli_versions` (~46 tokens)

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.

Input parameters:

- `products` (array)

Output parameters:

- `generated_at` (string)
- `products` (array)
- `rights_basis` (string)
- `schema_version` (number)

### `worlds_list_cli_models` (~68 tokens)

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.

Input parameters:

- `products` (array)

Output parameters:

- `catalog_version` (string)
- `catalogs` (array)
- `freshness` (object)
- `warning` (string)

### `worlds_plan_cli_work` (~185 tokens)

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.

Input parameters:

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

Output parameters:

- `assignments` (array)
- `available_clis` (array)
- `current_cli` (string)
- `evidence` (array)
- `handoff` (object)
- `planner_version` (string)
- `routing_basis` (string)
- `routing_principles` (array)
- `safety` (object)
- `strategy` (string)
- `task` (string)
- `uncertainties` (array)

### `worlds_advise_hard_problem` (~158 tokens)

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.

Input parameters:

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

Output parameters:

- `advisor_version` (string)
- `cross_provider_verdict` (string)
- `current_cli` (string)
- `decision_rule` (string)
- `evidence` (array)
- `live_validation_steps` (array)
- `provider_candidates` (array)
- `recommendation` (object)
- `safety` (object)
- `selection_scope` (string)
- `task` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-claude-world-worlds-knowledge/mcp#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 69
- 2026-08-01: 69

## Links

- Remote endpoint: https://mcp.claude-world.com/mcp
- Repository: https://github.com/claude-world/claude-world.com
- Website: https://claude-world.com/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/com-claude-world-worlds-knowledge/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-claude-world-worlds-knowledge/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-claude-world-worlds-knowledge/mcp