Keepfor.me is answering right now. Last checked 11 min ago. Last commit 7 Nov 2026.
Your personal library, readable by AI agents: durable snapshots, hybrid search, 46 MCP tools.
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
<p class="text-sm text-slate-400 text-center py-6">No highlights yet. Select text in the article to create one.</p>
</div>
{% endif %}
datalist.innerHTML = html;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.
claude mcp add keepfor-me --transport http https://app.keepfor.me/api/mcp
https://app.keepfor.me/api/mcp
[mcp_servers.keepfor-me]
url = "https://app.keepfor.me/api/mcp"
{
"mcpServers": {
"keepfor-me": {
"url": "https://app.keepfor.me/api/mcp"
}
}
}
{
"servers": {
"keepfor-me": {
"type": "http",
"url": "https://app.keepfor.me/api/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://app.keepfor.me/api/mcp | streamable-http | sign-in | 1173 ms | 11 min ago |
Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.
Personal context for every AI: search, read, and write back to your private Markdown library.
Your personal knowledge base and memory for AI agents: search, explore and feed your myBrain.
Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.
Personal AI memory layer on your own computer. Read/write durable memory across MCP clients.
Self-hosted knowledge backend for AI agents with hybrid search and MCP tools
Persistent memory for AI agents. 36+ MCP tools: encryption, decay, hybrid search, knowledge graph.
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
Answers built from our own checks of this server.