MCP server for AI security scanning. Detects prompt injections, jailbreaks, data
MCP server for AI security scanning. Detects prompt injections, jailbreaks, data exfiltration, and social engineering attacks in real-time using 42 regex patterns via the ClawGuard Shield API. Sub-10ms response times.
active Production-safe Score 97/100 http no auth
At a glance
| Endpoint | https://prompttools.co/api/v1/mcp |
|---|---|
| Source | https://glama.ai/mcp/servers/o84w5oktk7 |
| Transport | http |
| Tools | 2 |
| Auth | none |
| First seen | 2026-06-05 12:04:45 |
| Last checked | 2026-11-17 21:51:57 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 219 / 341 ms |
| Last successful check | 2026-11-17 21:51:57 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (2)
scan_text— Scan text for prompt injection attacks, jailbreak attempts, and other AI security threats. Detects 245 attack patterns across 15 languages.scan_mcp_config— Scan an MCP server configuration for security vulnerabilities: tool poisoning, permission escalation, data exfiltration vectors, hidden inst
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:51:57 | ✓ | ✓ | 120 ms | 95 | active |
| 2026-11-17 21:36:46 | ✓ | ✓ | 115 ms | 95 | active |
| 2026-11-17 21:21:33 | ✓ | ✓ | 318 ms | 92 | active |
| 2026-11-17 21:06:24 | ✓ | ✓ | 292 ms | 95 | active |
| 2026-11-17 20:51:07 | ✓ | ✓ | 276 ms | 95 | active |
| 2026-11-17 20:36:07 | ✓ | ✓ | 116 ms | 95 | active |
| 2026-11-17 20:21:07 | ✓ | ✓ | 118 ms | 95 | active |
| 2026-11-17 20:06:06 | ✓ | ✓ | 126 ms | 95 | active |
| 2026-11-17 19:50:16 | ✓ | ✓ | 118 ms | 95 | active |
| 2026-11-17 19:35:07 | ✓ | ✓ | 118 ms | 95 | active |
| 2026-11-17 19:19:56 | ✓ | ✓ | 115 ms | 95 | active |
| 2026-11-17 19:04:40 | ✓ | ✓ | 140 ms | 95 | active |
| 2026-11-17 18:49:28 | ✓ | ✓ | 115 ms | 95 | active |
| 2026-11-17 18:34:16 | ✓ | ✓ | 116 ms | 95 | active |
| 2026-11-17 18:19:09 | ✓ | ✓ | 121 ms | 95 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://prompttools.co/api/v1/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/prompttools-co-api-v1-mcp # JSON