Home / MCP registry index / com.stewai/stewai
StewAI
com.stewai/stewai in the official MCP registry.
Endpoint https://api.stewai.com/mcp.
The registry describes it as: Discover, run, inspect, build, test, and privately reuse AI workflows.
On 2026-10-28 we read its 14 tools, but part of what it advertised was cut before our rules saw it: a description or schema past the size we read, more tools than we read, or a tool list split across pages. Nothing in the part we read matched, but the rest was not checked: this is not a clean result.
Tools it advertises
check_recipe_build commit_recipe_build discover_stewai get_recipe_build get_recipe_build_activity get_recipe_preview get_results get_run review_recipe_build run_recipe run_recipe_acceptance search_recipes start_recipe_build update_recipe_build
Rather than checking back: subscribe to this server's tool changes (a feed, no account and no address needed). Tool names and dates only, never what a tool says.
Run this server? Show the check in your README
The badge reflects the latest read: 
[](https://lazaretto.dev/mcp-registry/com-stewai-stewai)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.