Clawbackai MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 39 installs a week from npm.
LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.
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 clawbackai-mcp -- npx -y clawbackai-mcp
{
"mcpServers": {
"clawbackai-mcp": {
"command": "npx",
"args": [
"-y",
"clawbackai-mcp"
]
}
}
}
[mcp_servers.clawbackai-mcp]
command = "npx"
args = ["-y", "clawbackai-mcp"]
{
"mcpServers": {
"clawbackai-mcp": {
"command": "npx",
"args": [
"-y",
"clawbackai-mcp"
]
}
}
}
{
"servers": {
"clawbackai-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"clawbackai-mcp"
]
}
}
}
LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.
Intelligent LLM routing proxy — 60-90% cost savings by auto-selecting the cheapest model
Routes each LLM completion to the cheapest capable provider across 8 providers (BYOK).
Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.
Find the cheapest AI model that passes your tests: audit repo models, build evals, routing, sizing
Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
Answers built from our own checks of this server.