AI agents invoke jest_adapter to trigger actions in InSite. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
A Jest adapter that integrates with browser automation will execute test scripts and browser actions. Running arbitrary test code in a browser automation context can trigger any browser operation, navigate pages, interact with elements, and execute JavaScript, giving it a broad blast radius if misused by an AI agent.
From the tool's definition "Integration adapter for Jest testing framework with browser automation capabilities" — runs test framework code with browser automation
Attacks that exploit this kind of access
Integration adapter for Jest testing framework with browser automation capabilities. It is categorised as a Execute tool in the InSite MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the InSite MCP server in PolicyLayer and add a rule for jest_adapter: 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 InSite. Nothing to install.
jest_adapter is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the jest_adapter 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 jest_adapter. 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.
jest_adapter is provided by the InSite MCP server (jowharshamshiri/insite). 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 →