Soulsketch runs on your own machine — the client starts it, so there is no endpoint to ping. 46 installs a week from npm. Last commit 14 Oct 2026.
Portable, user-owned AI memory packs: read, validate, fingerprint, diff, and observe
We read the source, 2 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.
const packPath = path.join(sanctumPath, packDirName);
<script src="https://d3js.org/d3.v7.min.js"></script>
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.
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 soulsketch -e 'SOULSKETCH_ALLOWED_ROOTS=<SOULSKETCH_ALLOWED_ROOTS>' -- npx -y @soulsketch/mcp-server
{
"mcpServers": {
"soulsketch": {
"command": "npx",
"args": [
"-y",
"@soulsketch/mcp-server"
],
"env": {
"SOULSKETCH_ALLOWED_ROOTS": "<SOULSKETCH_ALLOWED_ROOTS>"
}
}
}
}
[mcp_servers.soulsketch]
command = "npx"
args = ["-y", "@soulsketch/mcp-server"]
env = { SOULSKETCH_ALLOWED_ROOTS = "<SOULSKETCH_ALLOWED_ROOTS>" }
{
"mcpServers": {
"soulsketch": {
"command": "npx",
"args": [
"-y",
"@soulsketch/mcp-server"
],
"env": {
"SOULSKETCH_ALLOWED_ROOTS": "<SOULSKETCH_ALLOWED_ROOTS>"
}
}
}
}
{
"servers": {
"soulsketch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@soulsketch/mcp-server"
],
"env": {
"SOULSKETCH_ALLOWED_ROOTS": "<SOULSKETCH_ALLOWED_ROOTS>"
}
}
}
}
Put your own value in place of
<SOULSKETCH_ALLOWED_ROOTS> (Colon-separated absolute paths the server may access (your Soul-Sanctum memory repos)).
The author’s registry entry marks it as required.
Owned, portable working memory: a plain-files markdown brain any model can read and cite.
Private, portable memory and reusable skills for AI agents.
Portable AI memory as MCP tools: five reads and three controlled writes.
Person-owned AI memory: portable context for any MCP client.
Evidence-readiness MCP server: validate, audit, and score briefs, memos, and evidence packs.
Project memory for AI agents: read and keep the user's Listspace boards up to date.
Local-first AI memory MCP server. Record, recall and consolidate memory on your own machine.
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Answers built from our own checks of this server.