23 tools. 10 can modify or destroy data without limits.
2 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (bitrix24_delete_task_checklist_item, bitrix24_delete_task_dependency) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (bitrix24_add_task_checklist_item, bitrix24_add_task_dependency, bitrix24_create_project) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
bitrix24_delete_task_checklist_item:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
bitrix24_add_task_checklist_item:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
bitrix24_diagnose_permissions:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Bitrix24 Tasks server exposes 2 destructive tools including bitrix24_delete_task_checklist_item, bitrix24_delete_task_dependency. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Bitrix24 Tasks server has 8 write tools including bitrix24_add_task_checklist_item, bitrix24_add_task_dependency, bitrix24_create_project. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
23 tools across 3 categories: Destructive, Read, Write. 13 are read-only. 10 can modify, create, or delete data.
One line change. Instead of running the Bitrix24 Tasks server directly, prefix it with Intercept: intercept -c bitrix24-tasks.yaml -- npx -y @bitrix24-tasks-mcp-server. Download a pre-built policy from policylayer.com/policies/bitrix24-tasks and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.