AI agents invoke ng_update 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.
The ng_update command in Angular CLI updates packages and applies migration schematics, which can modify project files, dependencies, and code. This constitutes execution of update scripts/migrations that modify the codebase. The description 'Run' is nearly empty, lowering confidence, but the tool name and context of Angular CLI tools strongly suggest this executes the ng update command.
From the tool's definition Tool name 'ng_update' suggests running Angular CLI update command; description only says 'Run' which is uninformative
Documented attack patterns abuse exactly the kind of access ng_update 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_update:
{
"version": "1",
"default": "deny",
"tools": {
"ng_update": {
"limits": [
{
"counter": "ng_update_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ng_update 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_update: 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_update 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_update 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_update. 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_update 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.