prune_memories

THE RISK

Critical Risk

Why prune_memories needs a policy

Although memory deletion in an AI context does not affect financial systems or external data, permanent deletion of the AI system's persistent memory state represents a severe and irreversible loss. An agent with access to this tool could maliciously erase critical memory records (episodic, semantic, procedural, or strategic) that the AI relies on for continuity and decision-making.

From the tool's definition The tool description explicitly states 'Permanently delete memories' — the action is irreversible and cannot be undone. This meets the definition of Destructive: 'irreversibly deletes or overwrites data, or actions that cannot be undone.'

Documented attack patterns abuse exactly the kind of access prune_memories gives an agent:

POLICY

How to control prune_memories

PolicyLayer is an MCP gateway — it sits between your AI agents and AGI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for prune_memories:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "prune_memories"
  ]
}

prune_memories disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register AGI MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More AGI MCP Server tools

Destructive cleanup_expired_working_memory Clean up expired working memories Write consolidate_working_memory Consolidate multiple working memories into a single semantic memory Write activate_cluster Activate a memory cluster and get its associated memories Write archive_old_memories Archive old memories based on age and importance criteria Write create_memory Create a new memory with optional type-specific metadata Write create_memory_cluster Create a new memory cluster Write create_memory_relationship Create a relationship between two memories Write create_working_memory Create a temporary working memory with expiration

All 24 AGI MCP Server tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in AGI MCP Server → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about prune_memories

What does the prune_memories tool do? +

Permanently delete memories based on criteria. It is categorised as a Destructive tool in the AGI 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_memories? +

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

What risk level is prune_memories? +

prune_memories 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_memories? +

Yes. Add a rate_limit block to the prune_memories 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_memories completely? +

Set action: deny in the PolicyLayer policy for prune_memories. 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_memories? +

prune_memories is provided by the AGI MCP Server MCP server (quixiai/agi-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AGI MCP Server tool call.

Start from AGI MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →