mcpbeat Sign in

WorkingMemory MCP Server

by workingmemory Your server? Claim it
answering

WorkingMemory is answering right now. Last checked 10 min ago. It exposes 4 tools.

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

Uptime history 91 days of history · worst day 95%
91 days agonow
100.0%
Uptime 24h
91 of 91 checks
4
Tools
read from the server
216 ms
Response time
average over 24h
open, no key
Access
streamable-http

Nothing serious here today

Today is the operative word: we check WorkingMemory every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.

run in your terminal
claude mcp add memory --transport http https://app.workingmemory.ai/mcp
Settings → Connectors → Add custom connector, then paste this address
https://app.workingmemory.ai/mcp
~/.codex/config.toml
[mcp_servers.memory]
url = "https://app.workingmemory.ai/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "memory": {
      "url": "https://app.workingmemory.ai/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "memory": {
      "type": "http",
      "url": "https://app.workingmemory.ai/mcp"
    }
  }
}

Available tools 4

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

capture
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_id. Returns immediately; extraction happens in the background.
manage
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.
memory
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.
save
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 is split into individual memories automatically.

Endpoints

URLTransportStateLatencyChecked
https://app.workingmemory.ai/mcp streamable-http answering 77 ms 10 min ago

Alternatives to WorkingMemory

same job, measured the same way
Memory
by velixarai

Persistent memory for AI assistants. Store, search, and recall across sessions.

91 installs/wk local only
Engram
by getengram

Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.

answering
Goldhold
by jerrysrodz

Persistent memory for AI agents. Search, store, and recall across sessions.

93 installs/wk answering
Butlerbrain
by butlerbrain

Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.

answering
Brains
by spacecowboyian

Personal wiki and memory for AI assistants: store, search, and recall structured notes.

1 080 installs/wk local only
Taproot
by taproothq

Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.

answering
Memory MCP
by ragionex

Persistent memory for AI agents - save once, recall in every session, project and tool.

252 installs/wk local only
Amber
by ambermem

Long-term memory for AI assistants: permanent, portable across clients, searchable and exportable.

answering

WorkingMemory — questions

Answers built from our own checks of this server.

What can WorkingMemory do?
It exposes 4 tools, read directly from the server on our last check. Among them: capture_memory, manage_memory, save_memory, search_memory. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is WorkingMemory working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 216 ms. The bar chart above shows every period we have measured.
How do I connect WorkingMemory?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does WorkingMemory need an API key?
No. WorkingMemory completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is WorkingMemory?
It answers our handshake in 216 ms on average, which is faster than 66% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.