This record as markdown: /tools/kiln/cache-design-with-source.md
What cache_design_with_source does on Kiln
AI agents use cache_design_with_source to create or update resources in Kiln, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kiln environment.
Why cache_design_with_source is rated Medium
The name implies writing data to a cache (storing a design with its source), which is a Write operation. However, since the description is empty and uninformative, confidence is low. Based on naming convention alone, this appears to create or update cached design data, which is reversible and classifies as Write.
From the tool's definition Tool name 'cache_design_with_source' suggests storing/writing design data with source information. Description is empty.
Attacks that exploit this kind of access
The rule that runs cache_design_with_source safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Kiln, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cache_design_with_source, this is the rule to start with:
cache_design_with_source stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Kiln, apply this rule, and every cache_design_with_source call is checked against it from then on.
Questions about cache_design_with_source
cache_design_with_source is a write tool on the Kiln MCP server. It is categorised as a Write tool in the Kiln MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kiln MCP server in PolicyLayer and add a rule for cache_design_with_source: 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.
cache_design_with_source is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cache_design_with_source 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 cache_design_with_source. 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.
cache_design_with_source 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.
More on Kiln, and thousands of servers like it.
This server
Across the catalogue