AI agents call lint_rxjs to retrieve information from Rxjs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a static analysis tool that reads and examines RxJS code to identify issues and best practices. It has no side effects—it does not execute code, modify data, delete anything, or trigger external operations. The analysis is read-only inspection, fitting squarely in the Read category with low severity due to its purely informational nature and limited blast radius if misused by an AI agent.
From the tool's definition Tool performs 'lint' and 'analyze' operations on code snippets using regex-based pattern matching. Description explicitly states it performs analysis with 'no ESLint runtime required' and no modification of code or external systems.
Attacks that exploit this kind of access
Lint RxJS code snippets for common issues and best practices (regex-based best-effort analysis, no ESLint runtime required). It is categorised as a Read tool in the Rxjs MCP Server, which means it retrieves data without modifying state.
Register the Rxjs MCP server in PolicyLayer and add a rule for lint_rxjs: 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 Rxjs. Nothing to install.
lint_rxjs 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 lint_rxjs 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 lint_rxjs. 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.
lint_rxjs is provided by the Rxjs MCP server (shuji-bonji/rxjs-mcp-server). 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 →