AI agents call js.find_endpoints to retrieve information from VulneraMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to parse JavaScript to discover API endpoints, which is a read operation that retrieves information from code artifacts without executing it or modifying state. However, confidence is reduced from high to medium because the description is empty, making it impossible to confirm the exact behavior.
From the tool's definition Tool name 'js.find_endpoints' combined with sibling tools 'js.analyze', 'js.beautify', 'js.extract_secrets', and 'js.download' suggests static analysis of JavaScript code to identify endpoints.
Documented attack patterns abuse exactly the kind of access js.find_endpoints gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VulneraMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for js.find_endpoints:
{
"version": "1",
"default": "deny",
"tools": {
"js.find_endpoints": {}
}
}js.find_endpoints is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
js.find_endpoints. It is categorised as a Read tool in the VulneraMCP MCP Server, which means it retrieves data without modifying state.
Register the Vulnera MCP server in PolicyLayer and add a rule for js.find_endpoints: 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 VulneraMCP. Nothing to install.
js.find_endpoints 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 js.find_endpoints 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 js.find_endpoints. 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.
js.find_endpoints is provided by the Vulnera MCP server (telmon95/vulneramcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 47 VulneraMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
47 VulneraMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.