AI agents invoke core_install to trigger actions in MCP Arduino Server. 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.
Based on the tool name and server context, 'core_install' likely installs Arduino board cores (platform packages) via arduino-cli. Installing system-level packages/cores is an Execute-level operation as it modifies the development environment by downloading and installing software. Confidence is reduced due to the empty description.
From the tool's definition Tool name 'core_install' on a server that manages Arduino board cores via arduino-cli; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access core_install gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Arduino Server, and nothing reaches the server without passing your rules. This is the rule we recommend for core_install:
{
"version": "1",
"default": "deny",
"tools": {
"core_install": {
"limits": [
{
"counter": "core_install_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}core_install 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.
core_install. It is categorised as a Execute tool in the MCP Arduino Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Arduino Server MCP server in PolicyLayer and add a rule for core_install: 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 Arduino Server. Nothing to install.
core_install 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 core_install 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 core_install. 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.
core_install is provided by the MCP Arduino Server MCP server (volt23/mcp-arduino-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Arduino Server, 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.
21 MCP Arduino Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.