23 tools. 16 can modify or destroy data without limits.
3 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (clear_formatting, delete_comment, delete_footnote) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (accept_changes, add_comment, add_footnote) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Intercept sits between your agent and Safe Docx. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.
npx -y @policylayer/intercept scan -- npx -y @usejunior/safe-docx clear_formatting:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
accept_changes:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
extract_revisions:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Safe Docx server exposes 3 destructive tools including clear_formatting, delete_comment, delete_footnote. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Safe Docx server has 13 write tools including accept_changes, add_comment, add_footnote. 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. 7 are read-only. 16 can modify, create, or delete data.
One line change. Instead of running the Safe Docx server directly, prefix it with Intercept: intercept -c safe-docx.yaml -- npx -y @@usejunior/safe-docx. Download a pre-built policy from policylayer.com/policies/safe-docx and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
npx -y @policylayer/intercept init