WorkingMemory
Server Details
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool has a distinct primary purpose: capture for automated extraction, save for explicit storing, search for retrieval, and manage for deletion. However, capture_memory and save_memory both write to memory and could be confused, though their descriptions clarify the different use cases.
All tool names follow a consistent verb_noun pattern with 'memory' as the object (capture_memory, manage_memory, save_memory, search_memory). This makes the API predictable and easy to navigate.
Four tools is well-scoped for a working memory server. Each tool covers a necessary operation (write, search, manage) without bloat or redundancy.
The core memory lifecycle is covered: saving, searching, and deleting. A notable gap is the lack of an update/edit operation, but users can work around it by saving a new memory and deleting the old one.
Available Tools
4 toolscapture_memoryCapture memoryAInspect
Capture durable facts from a task you just completed (drafting an email, summarizing a document, making a decision), as a byproduct — the user does nothing. Pass the task output/content; durable facts are extracted and stored automatically. Always include your conversation id in client.conversation_id. Returns immediately; extraction happens in the background.
Inputs: task_content (required), client, task_description.
manage_memoryManage memoryADestructiveInspect
Manage an existing memory item. Currently supports deleting a memory by id (soft delete — recoverable for 30 days). Use search_memory to find the id first.
Inputs: id (required), action (required).
save_memorySave to memoryAInspect
Save a thought, insight, fact, or todo to the user's Working Memory. The text is parsed and stored as one or more structured memory items, searchable a moment later via search_memory. Also use this when the user pastes memories or notes brought from another assistant — pass the full pasted text; it is split into individual memories automatically.
Inputs: text (required), client.
search_memorySearch memoryARead-onlyInspect
Search the user's Working Memory for relevant past notes and facts. Use this when the user references something they may have stored earlier, or to find related context before answering. Always include your conversation id in client.conversation_id.
Inputs: query (required), k, client, dedupe_recent, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Persistent, portable memory for AI assistants — your private memory graph, from any MCP client.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA personal AI memory hub that stores and retrieves personal data from any MCP-enabled AI assistant, enabling persistent memory across conversations.5MIT
- AlicenseAqualityDmaintenanceProvides persistent memory for AI assistants via MCP, enabling them to store and recall facts, preferences, and tasks across conversations using either local file storage or a cloud backend with semantic search.514 npmMIT
- AlicenseCqualityBmaintenanceProvides persistent, local-first AI memory across sessions via MCP tools for storing, searching, and retrieving context from past interactions.31698 PyPI1MIT
- AlicenseAqualityDmaintenanceMCP server for persistent, semantic memory across AI sessions; store context, decisions, and learnings and recall them with natural language search.238 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.