Snapstate runs on your own machine — the client starts it, so there is no endpoint to ping. 25 installs a week from npm. Last commit 15 Apr 2026.
Persistent state for AI agent workflows. Save, resume, and replay multi-step workflows.
We read the source, 13 h ago · rules 3dff92dd89df
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
el.innerHTML = msg;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check Snapstate every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 snapstate -- npx -y snapstate-sdk
{
"mcpServers": {
"snapstate": {
"args": [
"-y",
"snapstate-sdk"
],
"command": "npx"
}
}
}
[mcp_servers.snapstate]
command = "npx"
args = ["-y", "snapstate-sdk"]
{
"mcpServers": {
"snapstate": {
"args": [
"-y",
"snapstate-sdk"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"snapstate": {
"args": [
"-y",
"snapstate-sdk"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SNAPSTATE_API_URL (SnapState API URL), SNAPSTATE_API_KEY (Your SnapState API key (starts with snp_)).
The author declared them in the registry entry; get the values from the project itself.
MCP State Sidecar: durable state persistence for multi-agent AI workflows
Shared versioned state for multi-agent AI workflows
Multi-provider search broker for AI agents: 14 providers, 12-step extraction, retrieval workflows.
Step-by-step observability for MCP agent workflows
Agent Workflow Engine — multi-step MCP workflows with per-step directives and validation.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.
Observe and operate Hatchet workflows from an AI agent — runs, logs, trigger, cancel, replay.
Answers built from our own checks of this server.