AI agents use annotate_schematic to create or update resources in Kicad — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kicad environment.
The tool name suggests modifying schematic annotations, which is a write operation on KiCad project data. The description is empty, reducing confidence slightly, but context from sibling write/modification tools and the server's stated purpose of 'read/write' operations supports Write classification.
From the tool's definition Tool name 'annotate_schematic' and server context showing it performs schematic modification (siblings include add_copper_zone, add_global_label, add_hierarchical_label, add_lib_symbol). Annotation typically modifies schematic metadata reversibly.
Attacks that exploit this kind of access
annotate_schematic. It is categorised as a Write tool in the Kicad MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kicad MCP server in PolicyLayer and add a rule for annotate_schematic: 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 Kicad. Nothing to install.
annotate_schematic 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 annotate_schematic 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 annotate_schematic. 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.
annotate_schematic is provided by the Kicad MCP server (productofamerica/mcp-server-kicad). 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 →