Mnema — AI Memory Layer MCP Server

by hoanglt1223 Your server? Claim it

not responding

Mnema — AI Memory Layer is listed as active in the registry but did not answer our last check.

Personal knowledge graph as an AI memory layer over MCP - read, save, and link your memories.

The linked repository no longer exists on GitHub — it was deleted or made private.

Uptime history 91 days of history · worst day 1%

91 days agonow

1.1%

Uptime 24h

1 of 91 checks

—

Tools

hidden behind auth

1946 ms

Response time

average over 24h

open, no key

Access

streamable-http

Mnema — AI Memory Layer does not always answer

Over the last week it answered 4.1% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mnema --transport http https://secondbrain.hoangha.shop/api/mcp

Settings → Connectors → Add custom connector, then paste this address

https://secondbrain.hoangha.shop/api/mcp

~/.codex/config.toml

[mcp_servers.mnema]
url = "https://secondbrain.hoangha.shop/api/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "mnema": {
      "url": "https://secondbrain.hoangha.shop/api/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mnema": {
      "type": "http",
      "url": "https://secondbrain.hoangha.shop/api/mcp"
    }
  }
}

Endpoints

URL	Transport	State	Latency	Checked
https://secondbrain.hoangha.shop/api/mcp	streamable-http	answering	52 ms	8 min ago

Alternatives to Mnema — AI Memory Layer

same job, measured the same way

Kairn

by primeline-ai

Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.

local only

Booboo

by jessymariau

Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP.

67 installs/wk local only

Booboo

by jessedu29260-netizen

Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP.

local only

by nnar1o

Local knowledge graph memory MCP server for AI assistants.

local only

Shelbymcp

by studio-moser

Knowledge-graph memory server for AI tools via MCP

55 installs/wk local only

Memoro

by circassian1977-byte

Personal AI memory layer on your own computer. Read/write durable memory across MCP clients.

27 installs/wk local only

MCP Neo4j Memory

by neo4j-contrib

MCP Neo4j Knowledge Graph Memory Server

5 477 installs/wk local only

PersonalKnowHow

by georgi-petkov

Live public demo: query one person's learning and work history as a knowledge graph via MCP.

4 tools answering

Mnema — AI Memory Layer — questions

Answers built from our own checks of this server.

Is Mnema — AI Memory Layer working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 1 of 91 checks got a reply (1.1%), average response time 1946 ms. The bar chart above shows every period we have measured.

Is Mnema — AI Memory Layer still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

The registry lists Mnema — AI Memory Layer as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect Mnema — AI Memory Layer?

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 Mnema — AI Memory Layer need an API key?

No. Mnema — AI Memory Layer completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. This is what we observed, not what the docs claim.