26 tools. 11 can modify or destroy data without limits.
2 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (peaka_delete_cache, peaka_delete_query) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (peaka_create_cache, peaka_create_cache_batch, peaka_create_query) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (peaka_execute_query, peaka_execute_sql_query, peaka_refresh_cache_full) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
peaka_delete_cache:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
peaka_create_cache:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
peaka_get_cache_statuses:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Peaka server exposes 2 destructive tools including peaka_delete_cache, peaka_delete_query. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Peaka server has 5 write tools including peaka_create_cache, peaka_create_cache_batch, peaka_create_query. 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.
26 tools across 4 categories: Destructive, Execute, Read, Write. 15 are read-only. 11 can modify, create, or delete data.
One line change. Instead of running the Peaka server directly, prefix it with Intercept: intercept -c peaka.yaml -- npx -y @@peaka/mcp-server-peaka. Download a pre-built policy from policylayer.com/policies/peaka 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.