AI agents invoke open_project to trigger actions in KiCad 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.
This tool triggers an external operation by launching/opening a KiCad application with a specified project. It doesn't merely read data — it causes an external program (KiCad) to execute and load a project, which constitutes triggering an external operation. Severity is medium as misuse could open unintended projects or interfere with active KiCad sessions.
From the tool's definition Open a KiCad project in KiCad
Documented attack patterns abuse exactly the kind of access open_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and KiCad MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for open_project:
{
"version": "1",
"default": "deny",
"tools": {
"open_project": {
"limits": [
{
"counter": "open_project_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} open_project 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.
Open a KiCad project in KiCad. It is categorised as a Execute tool in the KiCad MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the KiCad MCP Server MCP server in PolicyLayer and add a rule for open_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 KiCad MCP Server. Nothing to install.
open_project 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 open_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 open_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.
open_project is provided by the KiCad MCP Server MCP server (lamaalrajih/kicad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from KiCad MCP 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.
16 KiCad MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.