Install a CLI tool by name using an allowlisted package manager (brew, apt, npm, pip, cargo).
AI agents invoke install_tool to trigger actions in Need. 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.
Installing a CLI tool via a package manager executes system-level operations that modify the host environment by downloading and installing software. While it is partially reversible (tools can be uninstalled), the act of running arbitrary installs can introduce malicious packages, alter system state, and execute code during installation scripts.
From the tool's definition Install a CLI tool by name using an allowlisted package manager (brew, apt, npm, pip, cargo)
Documented attack patterns abuse exactly the kind of access install_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Need, and nothing reaches the server without passing your rules. This is the rule we recommend for install_tool:
{
"version": "1",
"default": "deny",
"tools": {
"install_tool": {
"limits": [
{
"counter": "install_tool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}install_tool 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.
Install a CLI tool by name using an allowlisted package manager (brew, apt, npm, pip, cargo). It is categorised as a Execute tool in the Need MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Need MCP server in PolicyLayer and add a rule for install_tool: 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 Need. Nothing to install.
install_tool 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 install_tool 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 install_tool. 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.
install_tool is provided by the Need MCP server (tuckerschreiber/need). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Need, 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.
3 Need tools catalogued and risk-classified — across an index of 43,000+ MCP servers.