10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 553 ms
- 1agent-cost-mcpfound in code, not yet checkedno passport yet
- log_cost
Log token usage and cost for a task. Call this after each AI interaction.
- log_cost
- 2AgentCostfound in code, not yet checkedno passport yet
- agentcost_preview
Free cost analysis of AI agent session logs. Returns cost breakdown, token counts, model split, tool usage, and top-5 expensive turns. Upload your Claude Code JSONL session log to see where your money goes. No payment required.
- agentcost_analyze
Full AI agent spend analysis with waste detection, per-tool cost attribution, and optimization recommendations. Paid via x402 micropayment ($5 Pro, $15 Full). Pro: waste patterns + recommendations. Full: + benchmarks, savings projections.
- agentcost_preview
- 3capy-fleetfound in code, not yet checkedno passport yet
- capy_usage
Report what your Capy agents have cost over a date range, split into LLM and VM dollars,
- capy_usage
- 4Metrx MCP Serverfound in code, not yet checkedno passport yet
- get_cost_summary
Get a comprehensive cost summary for your AI agent fleet.
- list_agents
List all AI agents in your organization with their status, category, and cost.
- get_cost_summary
- 5io.github.ufhouck/aicost-clifound in code, not yet checkedno passport yet
- get_ai_cost
Calculate the cost of an AI model usage based on tokens or units.
- get_ai_cost
- 6ai-usagesfound in code, not yet checkedno passport yet
MCP serverrajatpal96/ai-usages
- usage_this_week
Get this week's AI agent token consumption, cost breakdown, and top agents.
- usage_this_week
- 7Kopernfound in code, not yet checkedno passport yet
- kopern_list_agents
List all your Kopern agents (name, description, model, domain, grading score). No LLM cost.
- kopern_list_agents
- 8foremanfound in code, not yet checkedno passport yet
MCP servergbangbolaoluwagbemiga/foreman
- foreman_discover
List specialist AI agents available for hire on Foreman — each with its skill, price in USDC, and on-chain reputation. Use this to see what you can delegate.
- foreman_discover
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.