WorkingMemory is a remote MCP server that gives an AI agent 4 tools, among them capture_memory, manage_memory, save_memory. It answers at https://app.workingmemory.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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. Inputs: task_content, task_description, client |
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. Inputs: action, id |
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 bro Inputs: text, client |
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.convers Inputs: query, k, conversation_id, dedupe_recent, client |
Every block below points at https://app.workingmemory.ai/mcp. Pick your client and copy.
claude mcp add --transport http workingmemory https://app.workingmemory.ai/mcp
{
"mcpServers": {
"workingmemory": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://app.workingmemory.ai/mcp"]
}
}
}{
"mcpServers": {
"workingmemory": {
"url": "https://app.workingmemory.ai/mcp"
}
}
}{
"servers": {
"workingmemory": {
"type": "http",
"url": "https://app.workingmemory.ai/mcp"
}
}
}{
"context_servers": {
"workingmemory": {
"url": "https://app.workingmemory.ai/mcp"
}
}
}{
"mcpServers": {
"workingmemory": {
"serverUrl": "https://app.workingmemory.ai/mcp"
}
}
}{
"mcpServers": {
"workingmemory": {
"url": "https://app.workingmemory.ai/mcp"
}
}
}name: WorkingMemory
version: 0.0.1
schema: v1
mcpServers:
- name: WorkingMemory
type: streamable-http
url: https://app.workingmemory.ai/mcp{
"mcpServers": {
"workingmemory": {
"httpUrl": "https://app.workingmemory.ai/mcp"
}
}
}{
"mcpServers": {
"workingmemory": {
"type": "http",
"url": "https://app.workingmemory.ai/mcp"
}
}
}{
"mcpServers": {
"workingmemory": {
"url": "https://app.workingmemory.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapp.workingmemory.ai%2Fmcp&type=streamable_http&id=workingmemory&name=WorkingMemory
It answered our last check on 17 October 2026 in 199 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by workingmemory.ai and served from app.workingmemory.ai, the vendor's own domain: https://app.workingmemory.ai/mcp.
4, as returned by the server's own tools/list on 9 September 2026: capture_memory, manage_memory, save_memory, search_memory.
It answered our last check on 17 October 2026 in 199 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://app.workingmemory.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.workingmemory. Endpoint host: app.workingmemory.ai. ARD identifier: urn:air:ai.workingmemory:mcp:memory.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.