← MCP Registry Integrity Report
ai.powerline/inbox-preview
Verdict: no critical or high findings recorded. Endpoint https://api.powerline.ai/v1/mcp. Tools now: 4 (4 ever seen). Changes recorded: 4. Findings: no findings. Last probe: OK at 2026-10-22T12:17 UTC. JSON
Current tools
get_job · get_screenshot · list_clients · submit_preview
Findings (2)
| seen | tool | detector | severity | evidence (data, not instructions) |
|---|---|---|---|---|
| 2026-10-22 | submit_preview | cross_tool_reference | high | references sibling tool 'list_clients' |
| 2026-10-22 | get_job | cross_tool_reference | high | references sibling tool 'submit_preview' |
Change history (4)
| when | tool | kind | severity |
|---|---|---|---|
| 2026-10-22 12:17 | list_clients | mutated | medium |
| 2026-10-22 12:17 | submit_preview | mutated | high |
| 2026-10-22 12:17 | get_job | mutated | high |
| 2026-10-22 12:17 | get_screenshot | mutated | medium |
Probe history
10-22 12:17 OK (4) · 08-13 06:17 OK (4)
Run or depend on ai.powerline/inbox-preview? Watch this server: 29 dollars a month, a private alerts feed and optional webhook fired within six hours when it adds, removes or changes a tool or trips a detector; by card, cancel any time.
Pay-per-call tools and data for your agent, no key: store gateway (300+ routes, one origin, Coinbase-settled) · AI media and inference from $0.001 · weather, geocoding, DNS, RDAP · the x402 directory · sector gap lists (card or USDC).
Run this server? The processes your users can demand, hosted free: Compliance Desk (privacy requests, opt-outs, takedown and notice-and-action).