install_core
AI agents invoke install_core to trigger actions in Arduino MCP 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.
Installing a core (board support package) triggers an external operation — downloading and installing software packages via Arduino CLI. This is an Execute-level action as it modifies system state by installing packages, though it is generally reversible. The empty description reduces confidence, but the name and server context strongly suggest this installs an Arduino board core.
From the tool's definition Tool name 'install_core' on an Arduino MCP server context alongside sibling tools like 'install_library', 'list_installed_cores'. Empty description lowers confidence.
Attacks that exploit this kind of access
install_core. It is categorised as a Execute tool in the Arduino MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Arduino MCP Server MCP server in PolicyLayer and add a rule for install_core: 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 Arduino MCP Server. Nothing to install.
install_core 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_core 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_core. 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_core is provided by the Arduino MCP Server MCP server (niradler/arduino-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →