AI agents invoke nodejs_check_types to trigger actions in MCP DevTools Server. 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.
The tool executes a TypeScript type-checking process (e.g., invoking `tsc --noEmit` or similar). This runs an external compiler/toolchain process, making it an Execute category action. While it is typically read-only in effect, it triggers execution of an external program whose behavior depends on the project state.
From the tool's definition Run TypeScript type checking
Documented attack patterns abuse exactly the kind of access nodejs_check_types gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP DevTools Server, and nothing reaches the server without passing your rules. This is the rule we recommend for nodejs_check_types:
{
"version": "1",
"default": "deny",
"tools": {
"nodejs_check_types": {
"limits": [
{
"counter": "nodejs_check_types_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}nodejs_check_types stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run TypeScript type checking. It is categorised as a Execute tool in the MCP DevTools Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP DevTools Server MCP server in PolicyLayer and add a rule for nodejs_check_types: 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 MCP DevTools Server. Nothing to install.
nodejs_check_types 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 nodejs_check_types 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 nodejs_check_types. 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.
nodejs_check_types is provided by the MCP DevTools Server MCP server (rshade/mcp-devtools-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP DevTools Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
79 MCP DevTools Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.