LaunchChair runs on your own machine — the client starts it, so there is no endpoint to ping. 66 installs a week from npm.
Plan, validate, and build products and features with LaunchChair.
Nothing serious here today
Today is the operative word: we check LaunchChair every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 agent -e 'LAUNCHCHAIR_AGENT_TOKEN=<LAUNCHCHAIR_AGENT_TOKEN>' -- npx -y @launchchair/agent{
"mcpServers": {
"agent": {
"command": "npx",
"args": [
"-y",
"@launchchair/agent"
],
"env": {
"LAUNCHCHAIR_AGENT_TOKEN": "<LAUNCHCHAIR_AGENT_TOKEN>"
}
}
}
}[mcp_servers.agent]
command = "npx"
args = ["-y", "@launchchair/agent"]
env = { LAUNCHCHAIR_AGENT_TOKEN = "<LAUNCHCHAIR_AGENT_TOKEN>" }{
"mcpServers": {
"agent": {
"command": "npx",
"args": [
"-y",
"@launchchair/agent"
],
"env": {
"LAUNCHCHAIR_AGENT_TOKEN": "<LAUNCHCHAIR_AGENT_TOKEN>"
}
}
}
}{
"servers": {
"agent": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@launchchair/agent"
],
"env": {
"LAUNCHCHAIR_AGENT_TOKEN": "<LAUNCHCHAIR_AGENT_TOKEN>"
}
}
}
}Put your own value in place of
<LAUNCHCHAIR_AGENT_TOKEN> (LaunchChair Agent API token from Settings > API Access).
The author’s registry entry marks it as required.
Alternatives to LaunchChair
same job, measured the same wayBuild, explain, and validate cron expressions
Build validated football table and World Cup group prediction links with TablePredict.
Feature flags and kill switches. Turn a shipped feature off in production without a deploy.
Launch and manage online stores with AI agents: products, inventory, pricing, orders and promotions.
Build, launch and manage referral, affiliate and loyalty programs with RefRef from your AI agent.
Build, validate, simulate, and deploy walkerOS event pipelines
Validate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs.
Talk to roadmaps with AI. Query and manage bars, OKRs, ideas, and launches.
LaunchChair — questions
Answers built from our own checks of this server.