Subsidy-Exposure & Quota-Cliff Watch
Server Details
Quota-cliff watch: budgeted-vs-current quota diffing, shadow prices, pre-commit verdicts.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
check_pool and precommit_query both surface pool status, but one returns raw typed diff events while the other returns a verdict, so their boundaries are mostly clear. shadow_price and register_pool are clearly distinct. Minor ambiguity remains around when to use check_pool versus precommit_query.
All four names use consistent snake_case, with no camelCase or mixed casing. However, only check_pool and register_pool follow a clear verb_noun pattern; precommit_query and shadow_price are modifier/noun compounds, so the convention is slightly uneven.
Four tools fit a narrow subsidy/quota monitoring purpose, and each appears to have a role. The set is slightly thin and could reasonably include one or two lifecycle helpers without becoming bloated.
The core register/check/query/price flow exists, but there is no list/get/update/delete for pools and no explicit usage-reporting tool despite shadow_price depending on reported usage. Agents can work around some gaps if they know their pool, but lifecycle coverage is incomplete.
Available Tools
4 toolscheck_poolCInspect
Current typed diff events for your pool.
Inputs: pool_id (required).
precommit_queryBInspect
Pre-commit verdict OPEN / AT_RISK / CLIFFED ($0.01/call x402; first query per operator free). Send the payment in the X-PAYMENT header when the first call returns a 402 challenge in the REST surface.
Inputs: pool_id (required).
register_poolCInspect
Register a pool with its budgeted quota definition (structured terms).
Inputs: pool_id (required), budgeted_terms (required).
shadow_priceDInspect
Metered-vs-subsidized shadow price for reported usage.
Inputs: usage (required), metered (required), subsidized_paid_usd.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Diff gatekeeper, pre-merge review, unicode safety, SMT prover, dependency advisor.
Read-only AWS cost and security findings, priced in $/month, with a fix for each
FinOps assistant: query AWS, GCP and Azure cost, commitments, budgets and reports.
Goldbeater's daily Google Ads audit, read-only: each finding, its evidence, its value and its fix.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query live 5-hour and 7-day quota limits, per-model allowances, and user plan tiers from the local Google Antigravity 2.0 Language Server. It also forecasts planned task consumption and self-learns from real pre/post measurements, isolating parallel-chat noise.3 npmMIT
- AlicenseAqualityBmaintenanceEnables AI agents to monitor live token consumption and rate-limit windows across providers and assess whether expensive actions are justified before exhausting quotas, with optional budget guardrails.2122 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceProvides coding agents with pre-flight cost estimation by analyzing local logs to forecast token usage and quota impact before expensive work, exposing tools for remaining quota, per-task cost estimates, and attempt affordability.132 npmMIT
- AlicenseBqualityCmaintenanceThis MCP server gives AI coding agents continuous self-awareness of their remaining Google Antigravity quota across both 5-hour rolling and weekly entitlement windows, plus live session token consumption and context pressure for the active conversation. It enables agents to probe headroom between tool steps, checkpoint work gracefully before hitting rate limits, and govern subagent model choice — all at zero LLM token cost.3MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.