3 tools from the AI Scanner MCP Server, categorised by risk level.
View the AI Scanner policy →ai_inventory Get an inventory of all AI/LLM technologies used in a codebase — which SDKs are imported, which frameworks are integrated, which models are referen... 2/5 check_secrets Security check — scan a directory for exposed API tokens and hardcoded secrets only. Returns pass/fail with a list of any exposed credentials found... 2/5 scan_directory Scan a directory for LLM SDK usage, AI frameworks, exposed API tokens, and hardcoded secrets. Returns all findings grouped by type (token, secret, ... 2/5 The AI Scanner MCP server exposes 3 tools across 1 categories: Read.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the AI Scanner server.
AI Scanner tools are categorised as Read (3). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept