Letsclarify MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 23 installs a week from npm.
Human-in-the-Loop API: AI agents create forms, share URLs with humans, get JSON back.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 letsclarify-mcp -- npx -y @heisee/letsclarify-mcp
{
"mcpServers": {
"letsclarify-mcp": {
"args": [
"-y",
"@heisee/letsclarify-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.letsclarify-mcp]
command = "npx"
args = ["-y", "@heisee/letsclarify-mcp"]
{
"mcpServers": {
"letsclarify-mcp": {
"args": [
"-y",
"@heisee/letsclarify-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"letsclarify-mcp": {
"args": [
"-y",
"@heisee/letsclarify-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
LETSCLARIFY_API_KEY (Your LetsClarify API key (starts with lc_)).
The author declared them in the registry entry; get the values from the project itself.
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
Human-in-the-loop for AI agents. Submit choices, get a human decision.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
VantaGate MCP Server & OpenAPI integration - Human-in-the-Loop for AI Agents
WhatsApp MCP Server - Human-in-the-loop for AI agents via WhatsApp
Secure secret management with a Human-In-The-Loop (HITL) interceptor for agent mutations.
Impri MCP server — human-in-the-loop approval inbox for AI agents
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Answers built from our own checks of this server.