Everkeep runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 15 Oct 2026.
Your notes in one folder on your own server; AI clients read and edit it under write policies
We read the source, 22 h ago · rules ccca72095570
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
if (!dry) fs.writeFileSync(p.path, out, 'utf8');
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.
execFile(bin, [arg], { timeout: 5000 }, (err, stdout, stderr) => {
const given = d => (path.isAbsolute(d) ? d : path.join(vault, d));
'https://<words>.trycloudflare.com', 'trycloudflare.com', '/mcp', 'localhost', '127.0.0.1', '[::1]', '0.0.0.0', '--host 0.0.0.0',
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add everkeep -- npx -y everkeep
{
"mcpServers": {
"everkeep": {
"args": [
"-y",
"everkeep"
],
"command": "npx"
}
}
}
[mcp_servers.everkeep]
command = "npx"
args = ["-y", "everkeep"]
{
"mcpServers": {
"everkeep": {
"args": [
"-y",
"everkeep"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"everkeep": {
"args": [
"-y",
"everkeep"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
EVERKEEP_VAULT (Absolute path of the folder the server reads and edits (the vault)), EVERKEEP_CONFIG (Path of the JSON config file; optional).
The author declared them in the registry entry; get the values from the project itself.
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Markdown notes in folders, with files, that your AI assistant can read, write and organise.
Save notes in seconds. Your AI can then search, read, write and tag them over MCP.
An MCP server inside LibreOffice: agents read and edit your open Writer and Calc documents.
Google Keep-style notes app with an MCP server for AI agents to read/write notes.
Read and write your Fresh Jots notes from Claude, Cursor, and any MCP client.
MCP server for Polarion ALM — read and write documents and work items
MCP server for note.com: create, edit and retrieve posts.
Answers built from our own checks of this server.