JSDoc operations. Actions: check_consistency|check_types|generate
AI agents call jsdoc to retrieve information from Project Graph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The jsdoc tool performs static analysis and documentation generation on JSDoc comments. 'check_consistency' and 'check_types' are read operations that inspect code. 'generate' creates documentation output without executing code or modifying source files irreversibly. No destructive, financial, or execute-arbitrary-code semantics are present.
From the tool's definition Tool description states 'JSDoc operations' with actions: 'check_consistency|check_types|generate'. These are all read or documentation-generation operations that analyze existing code without modifying project state or executing arbitrary logic.
Attacks that exploit this kind of access
JSDoc operations. Actions: check_consistency|check_types|generate. It is categorised as a Read tool in the Project Graph MCP Server, which means it retrieves data without modifying state.
Register the Project Graph MCP server in PolicyLayer and add a rule for jsdoc: 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 Project Graph. Nothing to install.
jsdoc 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 jsdoc 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 jsdoc. 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.
jsdoc is provided by the Project Graph MCP server (rnd-pro/project-graph-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 →