Home / MCP registry index / com.claude-world/worlds-knowledge
AI Worlds CLI Knowledge
com.claude-world/worlds-knowledge in the official MCP registry.
Endpoint https://mcp.claude-world.com/mcp. Source: github.com/claude-world/worlds-knowledge-mcp.
The registry describes it as: Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
We read its 12 tools on 2026-10-26. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
worlds_search_knowledge worlds_get_document worlds_compare_cli_workflows worlds_list_catalog worlds_search_cli_reference worlds_get_cli_command worlds_get_cli_configuration worlds_get_cli_workflow worlds_list_cli_versions worlds_list_cli_models worlds_plan_cli_work worlds_advise_hard_problem
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/com-claude-world-worlds-knowledge)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.