Independent health, price and history for x402/MPP endpoints. Metered over x402; free grade on web.
Scored across 2 tools
The two tool descriptions are nearly copy-pasted boilerplate; only 'grade' adds 'current observation plus 7 days of counts,' while 'history' explains nothing about what it returns or how it differs. An agent cannot reliably tell which to call for a given need (current status vs. long-term trend), making misselection likely.
Both names follow a clean pattern: shared prefix 'probe402_endpoint_' plus a distinct suffix ('grade', 'history'). The suffixes are noun-ish rather than a verb_noun convention, but the set is internally consistent and readable.
Two tools is thin for an observatory that also implies endpoint lookup, discovery, and verification workflows. It is defensible for a narrowly scoped read-only service, but borders on under-specified rather than well-scoped.
The pair covers 'current grade' and 'history' retrieval for a known endpoint_id/url, but there is no way to enumerate or search endpoints, so an agent starting from scratch has no entry point. Coverage of the implied lifecycle (discover → check → track) is partial.
The Machine Commerce Observatory: independent readings of x402 and MPP endpoints — alive right now, quoting what, and how fast? Probed on a published schedule under one published rubric, every reading traceable to a retained capture. Blocked and rate-limited are told apart from unreachable at capture time, so a defended endpoint is never reported as dead. Call before paying an unfamiliar endpoint, or to check whether one you use has repriced or rotated its payTo. This tool is the FREE grade: current observation plus 7 days of counts, by endpoint_id or by url. The same record our published reports are written from.
Inputs: url, endpoint_id.
The Machine Commerce Observatory: independent readings of x402 and MPP endpoints — alive right now, quoting what, and how fast? Probed on a published schedule under one published rubric, every reading traceable to a retained capture. Blocked and rate-limited are told apart from unreachable at capture time, so a defended endpoint is never reported as dead. Call before paying an unfamiliar endpoint, or to check whether one you use has repriced or rotated its payTo.
Inputs: endpoint_id (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Live x402 endpoint trust/diligence check before you pay it. $0.02/call via x402.
Live health leaderboard of x402 paid endpoints, plus an MCP server readiness check
x402 endpoint and MCP server index: find paid APIs for agents, x402 checks and price benchmarks.
Free, read-only MCP subset of x402 Toolbox's cheap data endpoints, free via MCP.
Add one secure layer between your agents and this server.