Schema | openclaw-cost-tracker-mcp

openclaw-cost-tracker-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`OPENCLAW_COST_LOGS`	No	Path to the directory containing cost-log JSONL files (only used when backend is 'openclaw-jsonl'). Defaults to ~/.openclaw/cost-logs/.	~/.openclaw/cost-logs/
`OPENCLAW_COST_BACKEND`	Yes	Backend to use: 'mock' for sample data with deliberate anomalies and routing opportunities, or 'openclaw-jsonl' for parsing OpenClaw cost-log JSONL files.

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
cost_overviewA	Top-level cost summary for a window — total spend, request count, by-provider breakdown, top agents, top models, anomaly count. Use this first for a single-pane view.
costs_by_agentB	Per-agent cost breakdown — total spend + request count + avg cost-per-request + primary provider/model + share of total spend, sorted by cost descending.
costs_by_providerB	Per-provider cost breakdown — total spend + request count + token counts + share of total, sorted by cost descending.
find_cost_anomaliesA	Requests whose cost is `threshold_multiplier`x or more above their agent's median request cost. Default 3.0x. Surfaces giant-context-paste accidents, runaway loops, model regressions, etc.
top_cost_driversA	Highest-spend agents + models in the window — flat list, no per-provider or anomaly noise. Useful for 'where's our money going' digest format.
model_routing_recommendationsA	Suggestions to route some volume to cheaper providers/models — e.g., claude-sonnet-4 → gemini-2.5-flash for extraction-style work, gpt-4o → gpt-4o-mini for short chats. Each rec includes 30d estimated savings.
forecast_monthly_costA	Projects 30-day total spend from the observed window's run rate. Returns per-provider 30d projection + confidence note. Re-run with longer window for stability.

Interactive templates invoked by user choice

Name	Description
`diagnose-cost-spike`	Walk a cost-overview snapshot and explain a recent spike
`weekly-cost-digest`	Compose a 200-word weekly cost digest from the last 7 days

Contextual data attached and managed by the client

Name	Description
`Cost overview snapshot (7-day window)`	Full cost summary: total, by-provider, top agents, top models, anomaly count
`30-day cost forecast`	Projected 30-day total + per-provider, with confidence note
`Recent cost anomalies`	Requests flagged as 3x+ above their agent's median cost

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/temurkhan13/openclaw-cost-tracker-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server