AI agents call scan_project_dirs to retrieve information from Npm Dev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
scan_project_dirs performs discovery and introspection of project structure by locating and reading package.json files and dev script definitions. This is a non-destructive, read-only operation that gathers information about the system state. There is no modification, execution of scripts, deletion, or financial impact.
From the tool's definition Tool description translates to 'Search for package.json and dev scripts in projects'. The action is scanning/searching for files and their contents, which is purely informational retrieval with no side effects.
Attacks that exploit this kind of access
プロジェクト内のpackage.jsonとdevスクリプトを検索. It is categorised as a Read tool in the Npm Dev MCP Server, which means it retrieves data without modifying state.
Register the Npm Dev MCP server in PolicyLayer and add a rule for scan_project_dirs: 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 Npm Dev. Nothing to install.
scan_project_dirs 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_project_dirs 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_project_dirs. 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_project_dirs is provided by the Npm Dev MCP server (masamunet/npm-dev-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →