API 키, 비밀번호, 토큰 등 민감한 정보가 코드에 노출되어 있는지 검사
AI agents call scan-secrets to retrieve information from Security Scanner MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only security scan to detect hardcoded secrets in code. It retrieves and analyzes code content to identify vulnerabilities but does not execute code, modify files, delete data, or perform any side effects. The blast radius of misuse is minimal—an AI agent could only retrieve scan results, not cause damage. This is fundamentally a Read category operation (search/detect pattern).
From the tool's definition Tool name 'scan-secrets' and description indicate it 'checks whether sensitive information such as API keys, passwords, tokens, etc. is exposed in code.' The operation is a scan/inspection activity with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
API 키, 비밀번호, 토큰 등 민감한 정보가 코드에 노출되어 있는지 검사. It is categorised as a Read tool in the Security Scanner MCP MCP Server, which means it retrieves data without modifying state.
Register the Security Scanner MCP server in PolicyLayer and add a rule for scan-secrets: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Security Scanner MCP. Nothing to install.
scan-secrets is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the scan-secrets rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for scan-secrets. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
scan-secrets is provided by the Security Scanner MCP server (ongjin/security-scanner-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
scan-secrets is one line of Security Scanner's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →