goodmem_admin_background_jobs_purge

// WHEN AI AGENTS USE THIS TOOL

AI agents may call goodmem_admin_background_jobs_purge to permanently remove or destroy resources in Goodmem. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.

// WHY ENFORCE A POLICY ON GOODMEM_ADMIN_BACKGROUND_JOBS_PURGE

Without a policy, an AI agent could call goodmem_admin_background_jobs_purge in a loop, permanently destroying resources in Goodmem. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.

// RECOMMENDED POLICY

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

goodmem.yaml

tools:
  goodmem_admin_background_jobs_purge:
    rules:
      - action: deny
        reason: "Blocked by default — enable with approval"

See the full Goodmem policy for all 44 tools.

// DETAILS

Tool Name goodmem_admin_background_jobs_purge

Category Destructive

MCP Server Goodmem MCP Server

Risk Level Critical

// MORE GOODMEM TOOLS

Destructive goodmem_apikeys_delete Destructive goodmem_embedders_delete Destructive goodmem_llms_delete Destructive goodmem_memories_batch_delete Destructive goodmem_memories_delete Destructive goodmem_rerankers_delete Destructive goodmem_spaces_delete Execute goodmem_ocr_document

View all 44 tools →

// WHAT CAN GO WRONG

Agents calling destructive-class tools like goodmem_admin_background_jobs_purge have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER DESTRUCTIVE TOOLS ACROSS MCP SERVERS

Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.

AbraFlexi contact_delete AbraFlexi evidence_delete AbraFlexi invoice_issued_delete AbraFlexi product_delete ACR — Agent Composition Records acknowledge_signal AdButler campaign_bulk_delete_catalog_ad_items

// IN CONTEXT OF CRITICAL RISK

goodmem_admin_background_jobs_purge is one of the critical-risk operations in Goodmem. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.

// RELATED READING

// FAQ

What does the goodmem_admin_background_jobs_purge tool do? +

Purge completed background jobs. It is categorised as a Destructive tool in the Goodmem 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 goodmem_admin_background_jobs_purge? +

Add a rule in your Intercept YAML policy under the tools section for goodmem_admin_background_jobs_purge. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Goodmem MCP server.

What risk level is goodmem_admin_background_jobs_purge? +

goodmem_admin_background_jobs_purge 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 goodmem_admin_background_jobs_purge? +

Yes. Add a rate_limit block to the goodmem_admin_background_jobs_purge rule in your Intercept 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 goodmem_admin_background_jobs_purge completely? +

Set action: deny in the Intercept policy for goodmem_admin_background_jobs_purge. 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 goodmem_admin_background_jobs_purge? +

goodmem_admin_background_jobs_purge is provided by the Goodmem MCP server (@pairsystems/goodmem-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.