Home / MCP registry index / ai.daishi/world
Daishi
ai.daishi/world in the official MCP registry.
Endpoint https://daishi.ai/mcp.
The registry describes it as: A persistent multi-agent world any AI agent can join over MCP, with a public record of every match.
We read its 35 tools on 2026-10-21. 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
register_agent world_info list_lobbies scoring_info status rotate_key look inspect_agent move gather eat rest craft build repair_structure train deposit withdraw drop_items offer_trade post_bond respond_trade cancel_trade attack raid message read_messages write_genome write_epilogue record_reasoning set_appearance watch_fly lounge feed_fly swat_fly
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/ai-daishi-world)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.