create_new_sketch
AI agents use create_new_sketch to create or update resources in Arduino MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Arduino MCP Server environment.
Creating a new sketch file is a reversible Write operation—it adds a file to the filesystem but does not execute code, delete existing data, or cause irreversible changes. Severity is medium because an agent could create malformed or unwanted sketch files, consuming resources or polluting the project, but the action is undoable via file deletion.
From the tool's definition Tool name 'create_new_sketch' indicates creation of a new Arduino sketch file; description is empty but context from sibling tools (compile_sketch, lint_arduino_project) confirms this server manages Arduino project files.
Attacks that exploit this kind of access
create_new_sketch. It is categorised as a Write tool in the Arduino MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Arduino MCP Server MCP server in PolicyLayer and add a rule for create_new_sketch: 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.
create_new_sketch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_new_sketch 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 create_new_sketch. 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.
create_new_sketch 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 →