Power Strip Security
Security plugs for AI agents, paid per call with x402 (USDC): read a URL as clean markdown with prompt injection removed, scan content for prompt injection, audit an MCP server or an agent skill before using it. Not a conversational A2A agent: call the HTTP endpoints (see https://api.powerstripsecurity.workers.dev/openapi.json) or the MCP server at https://api.powerstripsecurity.workers.dev/mcp.
A2A readiness
Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here B, 95.3/100), which weighs availability, conformance, card completeness and speed. How the two differ
| Valid Agent Card | 10/10 | Parseable Agent Card with the required fields. |
| Live JSON-RPC | 0/25 | Endpoint did not answer (250 ms). |
| Protocol version | 5/10 | Declares pre-1.0 A2A 0.3.0. Upgrade to v1.x for full points. |
| JWS signature | 0/10 | Card is unsigned. |
| Uptime (30 days) | 15/15 | 3/3 probes succeeded; final after 5 probes in 30 days. |
| Skill declaration | 10/10 | Declares 4 skill(s) with structured metadata. |
| Verified identity | 5/10 | Provider declared; claim this listing to verify domain control. |
| Freshness + modern flags | 4/5 | seen in a source within 7 days. |
| Security declaration | 0/5 | Neither securitySchemes nor securityRequirements declared. |
Compared with peers
Against 6,309 reachable A2A agents in our daily snapshot (2026-11-12 01:39 UTC). Display only; it does not change search order.
- Readiness
- Higher than 40% of peers
- This listing 49 · peer median 54
- Latency
- Faster than 90% of peers
- This listing 182 ms · peer median 398 ms
Where it loses the most points, and how to win them back
- Live JSON-RPC −25
— Answer JSON-RPC at the URL the Agent Card declares.
Now: Endpoint did not answer (250 ms).
- JWS signature −10
— Sign the Agent Card (JWS).
Now: Card is unsigned.
- Protocol version −5
— Support the current protocol revision.
Now: Declares pre-1.0 A2A 0.3.0. Upgrade to v1.x for full points.
Skills
-
Safe web readerRead a URL (web page or PDF) as clean markdown, scanned for prompt injection. POST https://api.powerstripsecurity.workers.dev/v1/read, $0.005 per call with x402.securityprompt-injectionx402
-
Prompt-injection scannerScan HTML or text you already have for prompt injection. POST https://api.powerstripsecurity.workers.dev/v1/scan, $0.002 per call with x402.securityprompt-injectionx402
-
MCP server auditAudit an MCP server for tool poisoning before you connect. POST https://api.powerstripsecurity.workers.dev/v1/mcp-audit, $0.01 per call with x402.securityprompt-injectionx402
-
Agent skill auditAudit an agent skill or AGENTS.md before an agent loads it. POST https://api.powerstripsecurity.workers.dev/v1/skill-audit, $0.005 per call with x402.securityprompt-injectionx402
How to call
https://api.powerstripsecurity.workers.dev/
Listed in
Directories this entry was found in.