vision.render.cache_prune
Describe which cached render classes would be dropped.
This record as markdown: /tools/visionmcp/vision.render.cache-prune.md
What vision.render.cache_prune does on Visionmcp
AI agents call vision.render.cache_prune to retrieve information from Visionmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why vision.render.cache_prune is rated Low
This is a read-only operation that queries or describes the state of cached render classes without modifying or deleting them. The use of 'would be dropped' (conditional) rather than 'drops' or 'deletes' (imperative) indicates the tool previews the outcome of a potential cache pruning operation rather than performing it. No side effects occur from calling this tool.
From the tool's definition Tool name 'cache_prune' with description 'Describe which cached render classes would be dropped' — the verb is 'Describe' and 'would be dropped' indicates a hypothetical/preview operation, not an actual deletion.
Attacks that exploit this kind of access
The rule that runs vision.render.cache_prune safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Visionmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For vision.render.cache_prune, this is the rule to start with:
vision.render.cache_prune is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Visionmcp, apply this rule, and every vision.render.cache_prune call is checked against it from then on.
Questions about vision.render.cache_prune
Describe which cached render classes would be dropped. It is categorised as a Read tool in the Visionmcp MCP Server, which means it retrieves data without modifying state.
Register the Vision MCP server in PolicyLayer and add a rule for vision.render.cache_prune: 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 Visionmcp. Nothing to install.
vision.render.cache_prune 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 vision.render.cache_prune 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 vision.render.cache_prune. 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.
vision.render.cache_prune is provided by the Vision MCP server (joshuahickscorp/visionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vision, and thousands of servers like it.
This server
Across the catalogue