24 tools. 20 can modify or destroy data without limits.
3 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (confirm_password_reset, delete_record, request_password_reset) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (auth_refresh, authenticate_user, authenticate_with_oauth2) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
confirm_password_reset:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
auth_refresh:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
get_collection_schema:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The PocketBase MCP Server server exposes 3 destructive tools including confirm_password_reset, delete_record, request_password_reset. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The PocketBase MCP Server server has 17 write tools including auth_refresh, authenticate_user, authenticate_with_oauth2. 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.
24 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 20 can modify, create, or delete data.
One line change. Instead of running the PocketBase MCP Server server directly, prefix it with Intercept: intercept -c imatrixme-pocketbase-mcp-server.yaml -- npx -y @imatrixme/pocketbase-mcp-server. Download a pre-built policy from policylayer.com/policies/imatrixme-pocketbase-mcp-server 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.