clear_all_memories

THE RISK

Critical Risk

Why clear_all_memories needs a policy

This tool irreversibly deletes all data in the memory collection with no undo capability. The scope (all memories) and permanence (explicitly warned as irreversible) make this a destructive operation at critical severity—an agent misconfiguration or prompt injection could wipe an entire knowledge base instantly.

From the tool's definition Tool name 'clear_all_memories' and description stating 'Delete ALL memories' and '⚠️ Warning: this action is irreversible!' explicitly indicate permanent, unrecoverable deletion of data.

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

POLICY

How to control clear_all_memories

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

policy.json

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

clear_all_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 MCP Qdrant Semantic Search — 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 MCP Qdrant Semantic Search tools

Destructive delete_memory Delete a specific memory by its ID. The ID is returned when storing a memory. Write store_memory Store information in semantic memory. The information will be indexed and can be retrieved Read get_memory Retrieve a specific memory by its ID with all its details. Read get_stats Get statistics about the memory collection (total count, status, etc.). Read list_memories List all stored memories with pagination. Useful for exploring database content. Read search_memory Search for semantically similar information in memory. Returns the most relevant results b

All 7 MCP Qdrant Semantic Search 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 MCP Qdrant Semantic Search → 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 clear_all_memories

What does the clear_all_memories tool do? +

Delete ALL memories from the collection. ⚠️ Warning: this action is irreversible!. It is categorised as a Destructive tool in the MCP Qdrant Semantic Search 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 clear_all_memories? +

Register the MCP Qdrant Semantic Search MCP server in PolicyLayer and add a rule for clear_all_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 MCP Qdrant Semantic Search. Nothing to install.

What risk level is clear_all_memories? +

clear_all_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 clear_all_memories? +

Yes. Add a rate_limit block to the clear_all_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 clear_all_memories completely? +

Set action: deny in the PolicyLayer policy for clear_all_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 clear_all_memories? +

clear_all_memories is provided by the MCP Qdrant Semantic Search MCP server (muhammedehab35/mcp-qdrant-semantic-search). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Qdrant Semantic Search tool call.

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

CHECK YOUR STACK →