AI agents call model_files 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 retrieves or lists publicly available files from Thingiverse, a 3D model repository. It performs a read-only query operation without modifying data, executing code, or triggering external operations. The blast radius is minimal—even if an AI agent lists all files for a model, no irreversible changes occur. Severity is low because file listing is informational only.
From the tool's definition Tool name 'model_files' combined with description 'List downloadable files for a Thingiverse model' indicates a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List downloadable files for a Thingiverse model. 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 model_files: 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.
model_files 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 model_files 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 model_files. 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.
model_files 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 →