// MCP TOOL REFERENCE

prior_retract

Retract (soft delete) a knowledge entry you contributed. Removes it from search results. This cannot be undone.

Part of the Prior MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

cg3/prior Destructive Risk 4/5

// WHEN AI AGENTS USE THIS TOOL

AI agents may call prior_retract to permanently remove or destroy resources in Prior. 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 PRIOR_RETRACT

Without a policy, an AI agent could call prior_retract in a loop, permanently destroying resources in Prior. 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.

cg3-prior.yaml

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

See the full Prior policy for all 5 tools.

// DETAILS

Tool Name prior_retract

Category Destructive

MCP Server Prior MCP Server

Risk Level Critical

// MORE PRIOR TOOLS

Write prior_contribute Read prior_feedback Read prior_search Read prior_status

// WHAT CAN GO WRONG

Agents calling destructive-class tools like prior_retract 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 Agent Passport System — Cryptographic Identity for AI Agents remove_intent_card Agent Passport System — Cryptographic Identity for AI Agents revoke_delegation

// IN CONTEXT OF CRITICAL RISK

prior_retract is one of the critical-risk operations in Prior. 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 prior_retract tool do? +

Retract (soft delete) a knowledge entry you contributed. Removes it from search results. This cannot be undone.. It is categorised as a Destructive tool in the Prior 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 prior_retract? +

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

What risk level is prior_retract? +

prior_retract 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 prior_retract? +

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

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

prior_retract is provided by the Prior MCP server (cg3/prior). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

prior_retract

Enforce policies on Prior