Every AI coding tool wants its own config. Devin reads ~/.config/devin, Claude reads ~/.claude, Cursor keeps ~/.cursor/mcp.json, Codex wants TOML, Continue wants YAML. Set up the same MCP server in five tools and you maintain five copies of it - and five places for an API key to leak.
universal-ai-config is our answer: one unified store at ~/.agents/ that every provider reads from - or that you explicitly export to each provider's native format.
ai-config migrate - imports existing provider configs into ~/.agents/ (backs up originals, dedupes identical MCP servers, aliases conflicts)ai-config sync - exports back to native files: MCP servers, rules (as managed blocks), skills, provider settings. Opt-in per provider ("sync": true), with include/exclude scoping and --prune mirror modemcpServers, servers, context_servers, TOML tables, YAML lists)disabled: true on any MCP entry keeps it in the store as dormant inventory without ever exporting it.ai/ dirs for per-project config that merges over the user configv0.2.1 shipped a fix for a HIGH finding (CWE-427, uncontrolled search path): project_config() used to accept any .ai/ directory it walked into. In a shared or world-writable directory, another user could plant a config.json that merged into your settings - injecting provider credentials and arbitrary MCP servers, which sync would then write to provider files.
Now .ai/ is trusted only when both the directory and its parent are owned by the current user; anything else is skipped with a SecurityWarning.
uv tool install universal-ai-config # or pipx / pip
ai-config migrate # pull existing configs into ~/.agents/
ai-config status
Latest: v0.2.1 - the security fix plus Node-24 CI upgrades and changelog-driven release notes.