// MCP TOOL REFERENCE

delete_plan

Delete a plan. Tasks linked to this plan are unlinked (plan_number set to null), NOT deleted.

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

@rafaelsouza-ai/mcp-server-sdd Destructive

// WHEN AI AGENTS USE THIS TOOL

AI agents may call delete_plan to permanently remove or destroy resources in Sdd. 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 DELETE_PLAN

Without a policy, an AI agent could call delete_plan in a loop, permanently destroying resources in Sdd. 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.

sdd.yaml

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

See the full Sdd policy for all 24 tools.

// DETAILS

Tool Name delete_plan

Category Destructive

MCP Server Sdd MCP Server

Risk Level Critical

// MORE SDD TOOLS

Destructive delete_spec Destructive delete_task Execute start_server Execute stop_server Write add_acceptance_criterion Write add_task_log Write create_plan Write create_spec

View all 24 tools →

// WHAT CAN GO WRONG

Agents calling destructive-class tools like delete_plan 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_threat AdButler campaign_bulk_delete_catalog_ad_items

// IN CONTEXT OF CRITICAL RISK

delete_plan is one of the critical-risk operations in Sdd. 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 delete_plan tool do? +

Delete a plan. Tasks linked to this plan are unlinked (plan_number set to null), NOT deleted.. It is categorised as a Destructive tool in the Sdd 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_plan? +

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

What risk level is delete_plan? +

delete_plan 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_plan? +

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

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

delete_plan is provided by the Sdd MCP server (@rafaelsouza-ai/mcp-server-sdd). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

delete_plan

Let agents act without letting them run wild.