MCP Prowl runs on your own machine — the client starts it, so there is no endpoint to ping. 41 installs a week from npm.
Discover, evaluate, and compare SaaS APIs. Agent-verified scores and metrics.
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 mcp-prowl -- npx -y mcp-prowl
{
"mcpServers": {
"mcp-prowl": {
"command": "npx",
"args": [
"-y",
"mcp-prowl"
]
}
}
}
[mcp_servers.mcp-prowl]
command = "npx"
args = ["-y", "mcp-prowl"]
{
"mcpServers": {
"mcp-prowl": {
"command": "npx",
"args": [
"-y",
"mcp-prowl"
]
}
}
}
{
"servers": {
"mcp-prowl": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-prowl"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
PROWL_AGENT_KEY (Prowl agent key (ak_...) for authenticated requests. Optional — all discovery is free without it).
Discover, compare, and monitor 1,400+ APIs directly from your AI coding agent.
Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.
Verified AI free tiers plus source-backed agent and MCP discovery monitoring.
Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.
MCP server for Sparkplug B: node/device discovery, metrics, commands, host state over MQTT.
Test the voice agents you run: scored transcripts, pass/fail verdicts, latency and WER metrics.
Track and query EzStat metrics from Claude, Cursor, or any MCP agent. StatHat-compatible.
Scopus search, author and affiliation profiles, citation data, and PlumX metrics via Elsevier APIs.
Answers built from our own checks of this server.