todoist_delete_task

// WHEN AI AGENTS USE THIS TOOL

AI agents may call todoist_delete_task to permanently remove or destroy resources in Todoist-mcp-server-extended. 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 TODOIST_DELETE_TASK

Without a policy, an AI agent could call todoist_delete_task in a loop, permanently destroying resources in Todoist-mcp-server-extended. 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.

chrusic-todoist-mcp-server-extended.yaml

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

See the full Todoist-mcp-server-extended policy for all 19 tools.

// DETAILS

Tool Name todoist_delete_task

Category Destructive

MCP Server Todoist-mcp-server-extended MCP Server

Risk Level Critical

// MORE TODOIST-MCP-SERVER-EXTENDED TOOLS

Destructive todoist_delete_personal_label Destructive todoist_remove_shared_labels Write todoist_complete_task Write todoist_create_personal_label Write todoist_create_project Write todoist_create_project_section Write todoist_create_task Write todoist_rename_shared_labels

View all 19 tools →

// WHAT CAN GO WRONG

Agents calling destructive-class tools like todoist_delete_task 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

todoist_delete_task is one of the critical-risk operations in Todoist-mcp-server-extended. 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 todoist_delete_task tool do? +

Delete one or more tasks from Todoist. It is categorised as a Destructive tool in the Todoist-mcp-server-extended 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 todoist_delete_task? +

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

What risk level is todoist_delete_task? +

todoist_delete_task 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 todoist_delete_task? +

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

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

todoist_delete_task is provided by the Todoist-mcp-server-extended MCP server (Chrusic/todoist-mcp-server-extended). 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.