# Agent Cost Log

> Cost per run, tool, model and day for AI agents, from one call or an OpenTelemetry export.

- name: com.botrecipe/costlog
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.botrecipe%2Fcostlog
- tools: https://api.protogrid.dev/v1/servers/com.botrecipe%2Fcostlog/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "costlog": {
      "type": "http",
      "url": "https://costlog.cloudforbots.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-5d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: log_costs (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); cost_report (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); usage_and_upgrade (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 652 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 4 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 652 tokens to load them all
- tool set hash: 544a9005b158e803c51bc5f443598f4b
- badge: [![protogrid quality](https://protogrid.dev/badge/com.botrecipe/costlog.svg)](https://protogrid.dev/servers/com.botrecipe/costlog)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://costlog.cloudforbots.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (4)

- `cost_report`: 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.
- `log_costs`: 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.
- `usage_and_upgrade`: Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.
- `weekly_report`: 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.