prune_content

Analyze content_index for underperforming pages (thin or stale) and optionally archive them. Use action

Server Inkwell MCP Server mumega-com/inkwell
Category Destructive
Risk class Critical
Parameters 00 required

What prune_content does on Inkwell MCP Server

AI agents call prune_content to permanently remove resources in Inkwell MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Why prune_content needs a policy

The tool analyzes content and can optionally archive pages en masse. Archiving is typically a one-way or difficult-to-reverse operation at scale, especially when driven autonomously by an AI agent without human review of each item. Bulk removal of published content classifies this as Destructive with high severity due to the wide blast radius of potentially archiving large numbers of pages incorrectly.

From the tool's definition 'prune_content' with the ability to 'archive' underperforming pages described as 'thin or stale' — archiving content is a potentially irreversible bulk operation removing pages from active publication

Questions about prune_content

What does the prune_content tool do? +

Analyze content_index for underperforming pages (thin or stale) and optionally archive them. Use action. It is categorised as a Destructive tool in the Inkwell MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on prune_content? +

Register the Inkwell MCP Server MCP server in PolicyLayer and add a rule for prune_content: 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 Inkwell MCP Server. Nothing to install.

What risk level is prune_content? +

prune_content is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit prune_content? +

Yes. Add a rate_limit block to the prune_content 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.

How do I block prune_content completely? +

Set action: deny in the PolicyLayer policy for prune_content. 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.

What MCP server provides prune_content? +

prune_content is provided by the Inkwell MCP Server MCP server (mumega-com/inkwell). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.