Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@correctover-runtime-guard Diagnose this potential RCE in my tool call."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Real-time RCE/SSRF/Env Leak interception — 22µs P50.
pip install correctover-runtime-guard
correctover-runtime-guard startRelated MCP server: SentinelGate
Runtime guardrail for AI Agent tool calls — intercepts before execution:
RCE interception (CWE-78) — command injection in tool arguments
SSRF blocking (CWE-918) — metadata endpoint access, internal port scanning
Env leak prevention (CWE-200) — AWS_SECRET_ACCESS_KEY, OPENAI_API_KEY exfiltration
MCP Server mode — diagnose_error / get_fault_pattern / get_repair_suggestion
Metric | Value |
P50 latency | 22µs |
P99 latency | 89µs |
Overhead | <0.01% |
Detection rate | 99.7% |
50 interceptions/day — no credit card required.
Enterprise: $1,999/month — correctover.com/checkout
export CORRECTOVER_LICENSE_KEY=your-key-hereTool | Install | Description |
Security Scanner |
| MCP config security audit (14 checks) |
Self-Healing Test |
| Agent self-healing test suite |
Vulnerability Scan |
| 215 fault type scanner |
Compliance Check |
| OAuth 2.1 + CCS v1.0 |
Runtime Guard |
| 22µs RCE/SSRF interception |
MCP Server |
| 6-dimension validation |
Website: correctover.com · GitHub: github.com/Correctover
This server cannot be deployed
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
