Run temporal memory maintenance: decay relevance scores for old entities and optionally prune entities below the threshold. Keeps the knowledge graph fresh by deprioritizing stale information.
AI agents call decay_and_prune to permanently remove resources in CodeGraph — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs two actions: decaying relevance scores (Write) and pruning entities (Destructive). Per the rules, the most severe applicable category wins. Pruning entities from a knowledge graph removes them permanently ('keeps the knowledge graph fresh by deprioritizing stale information'), which constitutes irreversible deletion.
From the tool's definition 'optionally prune entities below the threshold' — pruning entities from the knowledge graph is an irreversible deletion of stored knowledge nodes
Documented attack patterns abuse exactly the kind of access decay_and_prune gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeGraph, and nothing reaches the server without passing your rules. This is the rule we recommend for decay_and_prune:
{
"version": "1",
"default": "deny",
"hide": [
"decay_and_prune"
]
}decay_and_prune disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Run temporal memory maintenance: decay relevance scores for old entities and optionally prune entities below the threshold. Keeps the knowledge graph fresh by deprioritizing stale information. It is categorised as a Destructive tool in the CodeGraph MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CodeGraph MCP server in PolicyLayer and add a rule for decay_and_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 CodeGraph. Nothing to install.
decay_and_prune is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the decay_and_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 decay_and_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.
decay_and_prune is provided by the CodeGraph MCP server (phoenixrr2113/codebase-graph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeGraph, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
18 CodeGraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.