Medium Risk

install_local_cli

Return no-data local install and MCP wiring commands. The remote server does not install anything and does not receive harness data.

Part of the Bring Your AI server.

install_local_cli can modify Bring Your AI data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE BRING YOUR AI →

Free to start. No card required.

AI agents use install_local_cli to create or modify resources in Bring Your AI. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call install_local_cli repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Bring Your AI.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "install_local_cli": {
      "limits": [
        {
          "counter": "install_local_cli_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Bring Your AI policy for all 7 tools.

Get this rule live on your own Bring Your AI server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY BRING YOUR AI →

These attack patterns abuse exactly the kind of access install_local_cli gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so install_local_cli only ever does what you allow.

SECURE BRING YOUR AI →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the install_local_cli tool do? +

Return no-data local install and MCP wiring commands. The remote server does not install anything and does not receive harness data.. It is categorised as a Write tool in the Bring Your AI MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on install_local_cli? +

Register the Bring Your AI MCP server in PolicyLayer and add a rule for install_local_cli: 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 Bring Your AI. Nothing to install.

What risk level is install_local_cli? +

install_local_cli is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit install_local_cli? +

Yes. Add a rate_limit block to the install_local_cli 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.

How do I block install_local_cli completely? +

Set action: deny in the PolicyLayer policy for install_local_cli. 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.

What MCP server provides install_local_cli? +

install_local_cli is provided by the Bring Your AI MCP server (https://bringyour.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Bring Your AI tool call.

Deterministic rules across all 7 Bring Your AI tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.