105 tools. 47 can modify or destroy data without limits.
6 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (delete, json_clear, json_del) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (bitmap_set, expire, hash_set) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (bitmap_pos, json_arrindex, json_arrtrim) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
delete:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
bitmap_set:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
bitmap_count:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Awslabs Valkey server exposes 6 destructive tools including delete, json_clear, json_del. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Awslabs Valkey server has 37 write tools including bitmap_set, expire, hash_set. 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.
105 tools across 4 categories: Destructive, Execute, Read, Write. 58 are read-only. 47 can modify, create, or delete data.
One line change. Instead of running the Awslabs Valkey server directly, prefix it with Intercept: intercept -c amazon-elasticache-memorydb-valkey-mcp-server.yaml -- npx -y @awslabs.valkey-mcp-server. Download a pre-built policy from policylayer.com/policies/amazon-elasticache-memorydb-valkey-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.