# Working Memory Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Working Memory

Save and search your personal notes, facts, and todos across all your conversations.

- Record: https://musedirectory.ai/connector/working-memory
- Category: Productivity
- Developer: Working Memory (https://workingmemory.ai)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 177ms, checked 2026-09-28T08:31:13Z
- Endpoint: https://app.workingmemory.ai/mcp
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-09-24T07:35:53Z)
- Source: Found in the official MCP Registry (ai.workingmemory/memory) https://registry.modelcontextprotocol.io/v0/servers?search=ai.workingmemory%2Fmemory

Persistent memory system that lets you save thoughts, insights, and notes to retrieve later. Search across all your saved memories by topic or keyword. Automatically extracts and stores key facts from completed tasks.

Example request: "Remember that I prefer my coffee with oat milk and no sugar when you help me order coffee next time."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Working Memory to help me. It is a free service with an MCP server at https://app.workingmemory.ai/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- 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 f
- 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 

Screening checks:
- MCP handshake: pass (Answered in 164ms)
- Domain against threat feeds (Cloudflare security DNS): pass (app.workingmemory.ai, workingmemory.ai not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (4 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 511 days ago)
- AI review of purpose and tool behavior: pass (No concerns)