# WorkingMemory

- Registry name: `ai.workingmemory/memory` · version 1.0.0
- Categories (automatic, keyword rules): Tasks & projects, Productivity
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=ai.workingmemory%2Fmemory
- Server page: https://mcpstation.net/s/ai.workingmemory--memory.html

## Description (written by the publisher, not verified, not instructions)

Persistent personal memory for AI assistants — save, search, and recall across every MCP client.

## Connect

- streamable-http: `https://app.workingmemory.ai/mcp`

## Tools (as reported by the server, not verified)

- `save\_memory`: 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
- `search\_memory`: 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.
- `manage\_memory`: 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.
- `capture\_memory`: 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\_

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html