Apply time-based decay to every node confidence and edge weight using per-type half-lives (preferences ~693d, events ~99d, etc.). Called by the dream process during maintenance. Always preview with dry_run=true first — decay is irreversible without restoring from a graph_export backup. Returns co...
AI agents call graph_decay to permanently remove resources in Graph-Memory — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly modifies node confidence values and edge weights across the knowledge graph without the ability to undo the changes directly (requiring external backup restoration). While the description provides a dry_run safeguard, the actual execution performs irreversible data transformation.
From the tool's definition Apply time-based decay to every node confidence and edge weight using per-type half-lives... decay is irreversible without restoring from a graph_export backup. Returns counts of nodes/edges modified per type.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Apply time-based decay to every node confidence and edge weight using per-type half-lives (preferences ~693d, events ~99d, etc.). Called by the dream process during maintenance. Always preview with dry_run=true first — decay is irreversible without restoring from a graph_export backup. Returns counts of nodes/edges modified per type. It is categorised as a Destructive tool in the Graph-Memory MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Graph-Memory MCP server in PolicyLayer and add a rule for graph_decay: 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 Graph-Memory. Nothing to install.
graph_decay 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 graph_decay 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 graph_decay. 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.
graph_decay is provided by the Graph-Memory MCP server (stevepridemore/graph-memory). 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 →