Filter components by criteria
AI agents call filter_components to retrieve information from KiCAD Schematic Manipulation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Filtering components is a read-only operation that retrieves a subset of components matching given criteria. It does not create, modify, delete, or execute anything. The tool name and description both suggest a pure query operation.
From the tool's definition 'Filter components by criteria' - filtering is a query/search operation with no side effects
Attacks that exploit this kind of access
Filter components by criteria. It is categorised as a Read tool in the KiCAD Schematic Manipulation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the KiCAD Schematic Manipulation MCP Server MCP server in PolicyLayer and add a rule for filter_components: 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 Schematic Manipulation MCP Server. Nothing to install.
filter_components is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the filter_components 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 filter_components. 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.
filter_components is provided by the KiCAD Schematic Manipulation MCP Server MCP server (richard-luc/kicad-schematic-manipulation). 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 →