delete_data

Delete records from memory.db table

SERVERProject Guardian MCP SOURCE1999azzar/project-guardian-mcp-server

Critical RISK CLASS

Category Destructive

Parameters 00 required

Recommended Hiddensee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/1999azzar-project-guardian-mcp-server/delete-data.md

WHAT IT DOES

What delete_data does on Project Guardian MCP

AI agents call delete_data to permanently remove resources in Project Guardian MCP, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

RISK

Why delete_data is rated Critical

Deletion of database records is irreversible and constitutes destructive action. While scoped to a specific SQLite database (memory.db) rather than system-wide destruction, the loss of persistent project context and entity tracking data would be significant.

From the tool's definition Tool name 'delete_data' combined with description 'Delete records from memory.db table' clearly indicates irreversible removal of data from the database.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs delete_data safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Project Guardian MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For delete_data, this is the rule to start with:

delete_data Hidden

delete_data is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.

View as policy code

policy.json

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

RESTRICT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Project Guardian MCP, apply this rule, and every delete_data call is checked against it from then on.

FAQ

Questions about delete_data

What does the delete_data tool do? +

Delete records from memory.db table. It is categorised as a Destructive tool in the Project Guardian MCP 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 delete_data? +

Register the Project Guardian MCP server in PolicyLayer and add a rule for delete_data: 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 Project Guardian MCP. Nothing to install.

What risk level is delete_data? +

delete_data 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 delete_data? +

Yes. Add a rate_limit block to the delete_data 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 delete_data completely? +

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

delete_data is provided by the Project Guardian MCP server (1999azzar/project-guardian-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Project Guardian, and thousands of servers like it.

This server

All 38 Project Guardian tools → Critical-risk tools on this server →

Across the catalogue

sms_delete_message on Twilio SMS MCP Server →delete_snapshot on Why Did You Render →calendar_delete_event on Templonix Lite MCP Server →delete_addon_domain on cPanel MCP Server → All critical-risk MCP tools → The MCP Attack Database →

Guides

Govern database agents →Blast radius →Tool call approval →