collect_basis_of_design
AI agents call collect_basis_of_design to retrieve information from Aerobic Design MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name indicates data collection/retrieval (basis of design parameters or specifications). The lack of description lowers confidence, but given the context of a design system where other tools handle state modification (clear_current_design_state, apply_state_corrections_tool, export_design_to_file), this appears to be an informational/read operation.
From the tool's definition Tool name 'collect_basis_of_design' suggests it retrieves or aggregates design basis information without modifying state. No description provided, limiting certainty.
Attacks that exploit this kind of access
collect_basis_of_design. It is categorised as a Read tool in the Aerobic Design MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Aerobic Design MCP Server MCP server in PolicyLayer and add a rule for collect_basis_of_design: 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 Aerobic Design MCP Server. Nothing to install.
collect_basis_of_design 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 collect_basis_of_design 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 collect_basis_of_design. 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.
collect_basis_of_design is provided by the Aerobic Design MCP Server MCP server (puran-water/aerobic-design-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 →