MoneyTools Inference Fidelity Audit
Server Details
Audit OpenAI-compatible / x402 inference sellers; quick check 0.005, bill check 0.003 USDC
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
The tools are mostly distinct: fidelity_audit is a full audit, fidelity_quick_check is a cheaper single-probe variant, fidelity_bill_check focuses on token billing, fidelity_models lists reference models, and fidelity_report provides a paid snapshot. The main overlap is that fidelity_report also includes model/pricing information that partly duplicates fidelity_models, but the paid aggregate vs free list distinction is clear enough.
All tools use a consistent fidelity_ prefix with snake_case names. The suffixes are predictable and readable, making the set easy to scan.
Five tools is well-scoped for an inference fidelity audit service. Each tool serves a distinct check, listing, or reporting purpose without excessive surface area.
The core audit lifecycle is covered: full audit, quick check, bill verification, model listing, and a paid report. Minor gaps exist around retrieving prior audit results or managing x402 payment state, but the main workflows are present.
Available Tools
5 toolsfidelity_auditBInspect
Audit a seller vs Cloudflare Workers AI reference. Free 2/day then 0.05 USDC. Auth header never stored.
Inputs: model (required), endpoint (required), apiKey, authHeader.
fidelity_bill_checkBRead-onlyIdempotentInspect
Recount visible tokens vs seller usage/charge. Free 5/day then 0.003 USDC.
Inputs: response (required), model, request, chargedUsd, +2 more.
fidelity_modelsBRead-onlyIdempotentInspect
List supported Workers AI reference models (free, read-only).
Inputs: no named parameters.
fidelity_quick_checkARead-onlyInspect
1-probe indicative check of a seller vs Cloudflare Workers AI reference (cheaper than a full audit). Free 3/day then 0.005 USDC via x402 (MCP: params._meta["x402/payment"]). Auth header never stored.
Inputs: model (required), endpoint (required), authHeader.
fidelity_reportARead-onlyIdempotentInspect
Paid, read-only: probe catalog + supported Workers AI models + pricing snapshot. 0.001 USDC via x402 (strictly paid — no free tier).
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Related MCP Connectors
AI code security audits via x402 USDC: $0.01 scans, $0.50 audits, $5 auto-fixes. SAST/SCA.
x402 settle: pay per call 0.002-0.003 USDC, no key; verify, receipts, advisory spend caps
Pay-per-call page reader, quote check, link check and x402 seller audit. USDC on Base via x402.
Pay-per-call checks for AI agents: sanctions, MiCA, French KYB, AI Act. USDC via x402.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceOpenAI-compatible inference broker that routes AI requests to the cheapest qualifying model and settles payments per token in USDC on Base L2 via x402 micropayments.MIT
- FlicenseNot gradedqualityCmaintenancePay-per-call agent tools (web reader, page extract, email/domain/site/wallet/token checks, screenshot, PDF) via x402 USDC micropayments, with 3 free trial calls per wallet.-
- AlicenseAqualityCmaintenanceEnables AI assistants and CLI users to run automated bytecode security audits of EVM smart contracts on Base Mainnet, detecting risky opcodes and interface signatures, scoring risk, and unlocking verified results via x402 USDC micropayments.3MIT
- AlicenseAqualityBmaintenanceBefore an AI agent pays an x402 endpoint, checks whether it's safe to pay: liveness, scam/anomaly scan (payTo hijack, bait-and-switch, honeypot), and on-chain receiver verification. ~70% of x402 endpoints are dead or scams.3MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.