Openclaw Cost Tracker MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 184 installs a week from pypi.
AI agent token-cost telemetry + 429 prediction. Per-agent attribution, anomaly + routing + quota.
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 openclaw-cost-tracker-mcp -- uvx openclaw-cost-tracker-mcp
{
"mcpServers": {
"openclaw-cost-tracker-mcp": {
"args": [
"openclaw-cost-tracker-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.openclaw-cost-tracker-mcp]
command = "uvx"
args = ["openclaw-cost-tracker-mcp"]
{
"mcpServers": {
"openclaw-cost-tracker-mcp": {
"args": [
"openclaw-cost-tracker-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"openclaw-cost-tracker-mcp": {
"args": [
"openclaw-cost-tracker-mcp"
],
"command": "uvx"
}
}
}
Cost Guard for Claude Code: per-tool ROI, subagent attribution, anomaly/forecast/budget guards.
Cross-venue prediction markets for AI agents: Polymarket + Kalshi, costed and attributed
Cross-venue prediction market routing for AI agents with arbitrage, quotes, history, and signals.
Pay-per-call ($0.01 USDC) model-routing for AI coding agents: which LLM to call, cost vs. quality.
Domain attribution and correlation for AI agents, with confidence and per-signal evidence.
Agent-first prediction markets on Base. Trade, quote, create markets via MCP.
Agent tracing, cost tracking, anomaly detection for LLM agents
Local-first memory and session continuity for AI coding agents over MCP. No cloud, no telemetry.
Answers built from our own checks of this server.