AI agents call recommend_adhesion_settings to retrieve information from Kiln without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or compute recommended adhesion parameters for 3D printers without side effects—no evidence of writing settings, executing commands, or destructive operations. The prefix 'recommend' suggests a read-only advisory function.
From the tool's definition Tool name 'recommend_adhesion_settings' indicates an advisory function that suggests settings for 3D printer adhesion; empty description limits clarity but naming pattern aligns with query/recommendation tools rather than commands that modify printer state.
Attacks that exploit this kind of access
recommend_adhesion_settings. It is categorised as a Read tool in the Kiln MCP Server, which means it retrieves data without modifying state.
Register the Kiln MCP server in PolicyLayer and add a rule for recommend_adhesion_settings: 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 Kiln. Nothing to install.
recommend_adhesion_settings 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 recommend_adhesion_settings 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 recommend_adhesion_settings. 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.
recommend_adhesion_settings is provided by the Kiln MCP server (codeofaxel/Kiln). 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 →