Detects undocumented API endpoints (Shadow APIs) and security risks
AI agents call detect_shadow_apis to retrieve information from Code Guard Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs security detection and analysis of API endpoints without making changes, executing code against targets, or deleting data. It retrieves information about shadow APIs to inform compliance and security posture. This is a read-only reconnaissance capability with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name contains 'detect' and description states 'Detects undocumented API endpoints...and security risks' — this is a scanning/analysis operation that identifies but does not modify or execute against targets.
Attacks that exploit this kind of access
Detects undocumented API endpoints (Shadow APIs) and security risks. It is categorised as a Read tool in the Code Guard Ai MCP Server, which means it retrieves data without modifying state.
Register the Code Guard Ai MCP server in PolicyLayer and add a rule for detect_shadow_apis: 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 Code Guard Ai. Nothing to install.
detect_shadow_apis 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 detect_shadow_apis 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 detect_shadow_apis. 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.
detect_shadow_apis is provided by the Code Guard Ai MCP server (negraodenio/code-guard-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
detect_shadow_apis is one line of Code Guard Ai'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 →