Agent Security MCP
Prompt injection detection, secret scanning, permission auditing
Versions
0.1.3latest0.1.20.1.10.1.0Tools 8
health_check Returns server health, uptime, version, and usage stats
scan_mcp_config Scan an MCP server configuration for security issues including dangerous commands, exposed secrets, network exposure, and container misconfigurations. Returns a risk score (0-100), issues found, and actionable recommendations.
detect_prompt_injection Analyze text for prompt injection attempts. Detects instruction overrides, identity manipulation, system prompt extraction, data exfiltration, delimiter attacks, encoded injections, and privilege escalation. Context-aware risk scoring.
validate_scope_contract Check if an agent action complies with its scope contract. Validates tool usage against allowlists, file access against permitted paths, and boundary constraints (no_network, read_only, no_exec, no_secrets).
scan_secrets Detect leaked secrets and credentials in text or code. Identifies API keys (OpenAI, AWS, GitHub, GCP, Stripe, Slack, Telegram), JWT tokens, database connection strings, private keys, and .env patterns. All values are masked in output.
audit_agent_permissions Audit an agent configuration for over-privileged access. Compares granted permissions against role-based expectations (researcher, analyst, developer, reviewer, orchestrator, monitor). Flags principle of least privilege violations.
generate_security_report Generate a comprehensive security assessment report for an agent deployment. Aggregates results from config scans and permission audits into a prioritized remediation plan with OWASP LLM Top 10 compliance notes.
detect_tool_poisoning Analyze an MCP tool definition for poisoning indicators — hidden instructions in descriptions that could manipulate agent behavior. Covers OWASP Agentic Top 10 tool poisoning attack vectors.
Permissions 1
env_vars low