MCP Servers / development / openclaw-cost-tracker-mcp

openclaw-cost-tracker-mcp

nonedevelopment

MCP server for AI agent token-cost telemetry + quota-window awareness across Anthropic, OpenAI, Gemini, Ollama, AWS Bedrock. Per-agent attribution, spend-spike detection, 429-prediction tools.

github ↗

Install

How to run this server

[ { "cmd": "pip install openclaw-cost-tracker-mcp", "imports": [] } ]

server path: openclaw-cost-tracker-mcp

Tools

What this server exposes

cost_overview

Get a summary of total spend over a specified time period, broken down by provider and agent.

top_cost_drivers

Identify the top cost-driving agents or models over a specified time period.

find_cost_anomalies

Detect spend spikes per agent using median-based anomaly detection.

model_routing_recommendations

Suggest cheaper model routing alternatives with estimated 30-day savings.

predict_429_in_window

Predict if a provider rate limit (429) will be hit before the current window resets, based on burn rate.

recommend_throttle_target

Recommend a safe burn rate to avoid hitting provider rate limits, given a target buffer percentage.

Configuration

Environment & auth

authnone

Resources

githubhttps://github.com/temurkhan13/openclaw-cost-tracker-mcp ↗