KLYPIX Project Brain runs on your own machine — the client starts it, so there is no endpoint to ping. 648 installs a week from npm. Last commit 16 Sep 2026.
Active state management for multi-agent coding: a shared, versioned project brain over MCP.
We read the source, 1 h ago · rules 3dff92dd89df
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 child = spawn(process.execPath, [
const entry = path.join(base, f);
Object.entries(process.env).filter(([, value]) => typeof value === 'string'),
world.innerHTML = frag.join('') + `<svg id="edges" width="1" height="1"><defs>${markers}</defs>${paths.join('')}</svg>`;
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 klypix-mcp -- npx -y klypix-mcp
{
"mcpServers": {
"klypix-mcp": {
"args": [
"-y",
"klypix-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.klypix-mcp]
command = "npx"
args = ["-y", "klypix-mcp"]
{
"mcpServers": {
"klypix-mcp": {
"args": [
"-y",
"klypix-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"klypix-mcp": {
"args": [
"-y",
"klypix-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
KLYPIX_VAULT (Alternative to --vault: absolute path to the folder holding your .klypix canvases. The --vault argument takes precedence.).
The author declared them in the registry entry; get the values from the project itself.
Shared versioned state for multi-agent AI workflows
Shared project wiki for AI agents: read and write pages, next actions, and activity logs over MCP.
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
MCP server for Generate-Data.com: dataset generation, AI schema design, Project management.
Shared task layer for AI coding agents. One MCP surface: task_search, task_get, task_mutate.
MCP server for Linear project management and issue tracking
Project management for coding agents. Bugs, features, sprints. Streamable HTTP + SSE remotes.
MCP server for checking package versions across multiple package managers
Answers built from our own checks of this server.