AI agents use kicad.save_project to create or update resources in Eda — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Eda environment.
The tool saves a KiCad project, which creates or modifies project files reversibly. This is a Write operation rather than Destructive because saving is non-destructive and reversible (previous versions can be recovered). High severity is appropriate because an AI agent that unexpectedly saves a project could overwrite user work or corrupt design state if called at the wrong time or with incorrect project context.
From the tool's definition Tool name is 'kicad.save_project' which indicates persisting/writing project state to storage. Description is empty, but the verb 'save' in the context of KiCad design files clearly indicates a write operation that modifies project data on disk.
Attacks that exploit this kind of access
kicad.save_project. It is categorised as a Write tool in the Eda MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Eda MCP server in PolicyLayer and add a rule for kicad.save_project: 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 Eda. Nothing to install.
kicad.save_project 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 kicad.save_project 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 kicad.save_project. 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.
kicad.save_project is provided by the Eda MCP server (saeronlab/eda-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 →