AI agents invoke ng_run to trigger actions in Mcp Angular Cli. 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.
This tool executes Angular CLI operations whose effects depend on the project configuration and arguments provided. While not destructive by default, 'ng run' can trigger arbitrary scripts, build pipelines, and external tool invocations. An AI agent misusing this could execute malicious scripts, alter build outputs, or trigger unintended side effects in a development environment.
From the tool's definition Tool name 'ng_run' and description 'Run' indicate execution of Angular CLI commands. The sibling tools (ng_add, ng_generate, ng_new, ng_update) confirm this is an Angular development server that executes build/development operations.
Documented attack patterns abuse exactly the kind of access ng_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Angular Cli, and nothing reaches the server without passing your rules. This is the rule we recommend for ng_run:
{
"version": "1",
"default": "deny",
"tools": {
"ng_run": {
"limits": [
{
"counter": "ng_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ng_run 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. It is categorised as a Execute tool in the Mcp Angular Cli MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Angular Cli MCP server in PolicyLayer and add a rule for ng_run: 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 Angular Cli. Nothing to install.
ng_run 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 ng_run 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 ng_run. 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.
ng_run is provided by the Mcp Angular Cli MCP server (talzach/mcp-angular-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Angular Cli, 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.
5 Mcp Angular Cli tools catalogued and risk-classified — across an index of 43,000+ MCP servers.