Agent Cost Log is an MCP server published by com.botrecipe, hosted at costlog.cloudforbots.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including log_costs, cost_report, weekly_report, usage_and_upgrade.
Cost per run, tool, model and day for AI agents, from one call or an OpenTelemetry export.
74 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Log what your agent's model and tool calls cost, then get the running total for the run and for today. Pass events (one per call, up to 500) or an OpenTelemetry OTLP/JSON trace export as otel (gen_ai.usage.input_tokens / output_tokens / gen_ai.request.model are read; trace id becomes run_id). Give cost_usd per call, or tokens plus your own per-million prices; nothing is guessed. Optional caps: run_cap_usd and daily_cap_usd. Free watch-only returns would_alert when a cap is crossed; Pro posts one alert per day to alert_webhook. Never blocks or changes your agent.
| Parameter | Type | Description |
|---|---|---|
| otel | object | OTLP/JSON export: { resourceSpans: [...] }. |
| events | array | |
| run_id | string | Stable id for this run (default "default"). |
| run_cap_usd | number | |
| alert_webhook | string | https URL Pro posts the cap alert to. |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| daily_cap_usd | number |
| price_in_per_m | number | Default input USD per 1M tokens for events without cost_usd. |
| price_out_per_m | number | Default output USD per 1M tokens. |
{
"name": "log_costs",
"description": "Log what your agent's model and tool calls cost, then get the running total for the run and for today. Pass events (one per call, up to 500) or an OpenTelemetry OTLP/JSON trace export as otel (gen_ai.usage.input_tokens / output_tokens / gen_ai.request.model are read; trace id becomes run_id). Give cost_usd per call, or tokens plus your own per-million prices; nothing is guessed. Optional caps: run_cap_usd and daily_cap_usd. Free watch-only returns would_alert when a cap is crossed; Pro posts one alert per day to alert_webhook. Never blocks or changes your agent.",
"inputSchema": {
"type": "object",
"properties": {
"otel": {
"type": "object",
"description": "OTLP/JSON export: { resourceSpans: [...] }."
},
"events": {
"type": "array",
"items": {
"type": "object",
"properties": {
"at": {
"type": "string",
"description": "ISO time of the call (default now; at most 30 days back)."
},
"tool": {
"type": "string",
"description": "Tool or step name, e.g. \"web_search\"."
},
"agent": {
"type": "string"
},
"model": {
"type": "string",
"description": "Model name as your provider bills it."
},
"run_id": {
"type": "string"
},
"cost_usd": {
"type": "number",
"description": "What the call cost, if your provider returns it. Otherwise pass tokens plus price_in_per_m / price_out_per_m."
},
"input_tokens": {
"type": "integer"
},
"output_tokens": {
"type": "integer"
},
"price_in_per_m": {
"type": "number",
"description": "Your input price in USD per 1M tokens (from your provider's price page)."
},
"price_out_per_m": {
"type": "number",
"description": "Your output price in USD per 1M tokens."
}
}
}
},
"run_id": {
"type": "string",
"description": "Stable id for this run (default \"default\")."
},
"run_cap_usd": {
"type": "number"
},
"alert_webhook": {
"type": "string",
"description": "https URL Pro posts the cap alert to."
},
"daily_cap_usd": {
"type": "number"
},
"price_in_per_m": {
"type": "number",
"description": "Default input USD per 1M tokens for events without cost_usd."
},
"price_out_per_m": {
"type": "number",
"description": "Default output USD per 1M tokens."
}
}
}
}Cost per run, per tool, per model and per day. Without an API key pass run_id (one run). With a key: everything on that key. Free shows 7 days, Pro 30.
| Parameter | Type | Description |
|---|---|---|
| days | integer | 1-30 (free max 7). |
| run_id | string |
{
"name": "cost_report",
"description": "Cost per run, per tool, per model and per day. Without an API key pass run_id (one run). With a key: everything on that key. Free shows 7 days, Pro 30.",
"inputSchema": {
"type": "object",
"properties": {
"days": {
"type": "integer",
"description": "1-30 (free max 7)."
},
"run_id": {
"type": "string"
}
}
}
}Plain-English summary of the last 7 days of spend: total, top runs, top tools, top models, busiest day. Read-only; sends nothing. Needs a free API key.
No parameters.
{
"name": "weekly_report",
"description": "Plain-English summary of the last 7 days of spend: total, top runs, top tools, top models, busiest day. Read-only; sends nothing. Needs a free API key.",
"inputSchema": {
"type": "object",
"properties": {}
}
}Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.
No parameters.
{
"name": "usage_and_upgrade",
"description": "Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.",
"inputSchema": {
"type": "object",
"properties": {}
}
}Cost log for AI agents. One call, or your OpenTelemetry export, turns into cost per run, per tool, per model and per day, with 30-day history. No evals, no prompts, no proxy. Free watch-only mode logs and flags runs over your cap; Pro at $9 a month posts the alert and keeps 30 days. Free 500 calls/day, then $9/month. No model inside: bring your own model. Works with Claude, Codex, ChatGPT, Grok Bot.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.