Runs Nx workspace commands and returns structured per-project task results with cache status.
AI agents invoke nx to trigger actions in Github. 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 arbitrary Nx workspace commands (which can include build, test, deploy, generate, affected, etc.). This is a command execution tool with significant blast radius since Nx commands can trigger deployments, generate/modify files, run scripts, and affect entire monorepo workspaces. It spans Write and Execute at minimum; Execute is the dominant category.
From the tool's definition 'Runs Nx workspace commands' — actively executes build/test/deploy tasks in the workspace
Documented attack patterns abuse exactly the kind of access nx gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Github, and nothing reaches the server without passing your rules. This is the rule we recommend for nx:
{
"version": "1",
"default": "deny",
"tools": {
"nx": {
"limits": [
{
"counter": "nx_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}nx 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.
Runs Nx workspace commands and returns structured per-project task results with cache status. It is categorised as a Execute tool in the Github MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Github MCP server in PolicyLayer and add a rule for nx: 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 Github. Nothing to install.
nx 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 nx 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 nx. 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.
nx is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Github, 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.
202 Github tools catalogued and risk-classified — across an index of 43,000+ MCP servers.