TypeSafe AI Documentation MCP Server
Hosted, anonymous, read-mostly MCP server over the published TypeSafe documentation corpus. Three tools: search_type_safe_ai (knowledge-base search), query_docs_filesystem_type_safe_ai (read-only rg/tree/head over a virtualised in-memory filesystem of the docs) and submit_feedback (the one write, reporting a documentation defect). It does NOT expose the System One evaluation endpoint — an agent can read everything about Jev over MCP and call none of it.