A
licenseNot graded
qualityB
maintenanceEnables AI agents to share a unified profile—skills and memory—across different agent tools via a single MCP server, so they maintain context and recall preferences everywhere.
Apache 2.0
OpenPrefs
by ai.openprefs
Server Details
One place for your preferences, portable across every AI assistant and agent.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP
- URL
- ChatGPT
- –
- Claude
- –
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
A persistent AI self you own — memory, persona, judgment — portable across all your AI hosts.
Personal AI memory — gives every AI agent shared, persistent memory of you
A profile you control: gives your AI your role, projects and preferences, across ChatGPT and Claude.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants across platforms to share memory, recall facts, preferences, and conversation history, creating a unified cognitive system.MIT
- FlicenseNot gradedqualityAmaintenanceGives MCP-compatible coding tools a shared, local-first store of your identity, preferences, decisions, and lessons, so agents start from an approved picture of you instead of a blank slate. Everything lives in inspectable local files that you can preview, edit, approve, or override, and that follow you across tools like Claude Code, Codex, Cursor, and Windsurf.-
- FlicenseNot gradedqualityAmaintenanceEnables multiple MCP-compatible coding tools to start from one local, user-owned identity and long-term knowledge store — preferences, quality bars, lessons, decisions, and project context — instead of rebuilding that understanding per tool or chat. Everything the agent receives stays inspectable, editable, overridable, and governed by user approval before it is shared.-
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.