polymnemo
Server Details
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
Glama couldn't complete the latest health check. 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
- 20.2% over 22 days
- OAuth
- Requires browser extension
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- PCBZ/polymnemo
- GitHub Stars
- 0
- Server Listing
- polymnemo
TDQS
Scored across 12 tools
Each tool maps cleanly to one operation: remembering/searching/listing/updating/deleting memories, the media upload lifecycle, or session save/load. The conceptually close pairs like recall/list_memories and remember/save_session are clearly distinguished by purpose and result shape.
Most tools follow a verb_noun pattern such as create_upload, get_memory, list_memories, and save_session. A few single-word verbs like remember, recall, forget, ping, and update break the pattern, but the naming remains readable and not chaotic.
Twelve tools cover memory, media, and session workflows without redundancy, and each tool earns its place in the lifecycle. This is well within the ideal scope for a server of this purpose.
Memory CRUD is well covered with remember, get_memory, list_memories, recall, update, and forget, and media uploads have create, confirm, and download support. Session support is thinner—only save and load—so explicit session listing or deletion would need to be inferred through memory ids, which is a minor gap.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
12 tool updates
- First observed
confirm_upload - First observed
create_upload - First observed
forget - First observed
get_download_url - First observed
get_memory - First observed
list_memories - First observed
load_session - First observed
ping - First observed
recall - First observed
remember - First observed
save_session - First observed
update
Related MCP Connectors
Cross-session memory for AI agents with a Source Receipt for every memory, over MCP.
Persistent memory for AI agents to retain, retrieve, and recall conversation context through MCP.
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
Persistent, portable memory for AI assistants — your private memory graph, from any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceSelf-hosted long-term memory for AI agents: MCP server with hierarchical recall over pgvector.32 npm14MIT
- AlicenseNot gradedqualityDmaintenancePersistent, semantically-searchable memory for AI agents using local PostgreSQL, pgvector, and Ollama embeddings, exposed via MCP with hybrid retrieval, knowledge graph, and auto-recall hook.3 npmMIT
- AlicenseAqualityBmaintenanceA personal memory MCP server that ingests AI agent conversation logs from multiple platforms into a searchable PostgreSQL+pgvector database, enabling cross-session recall of past reasoning and decisions.6MIT
- AlicenseNot gradedqualityCmaintenanceFramework-agnostic MCP server for agent memory with Postgres + pgvector, enabling persistent memory, recall, and task management across sessions.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.