9 tools. 4 can modify or destroy data without limits.
4 write tools that can modify data. Rate limits recommended.
Last updated:
Write operations (generate_report, generate_summary, knowledge_add_node) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (deep_research) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
generate_report:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
analyze_content:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
The Katashiro server has 3 write tools including generate_report, generate_summary, knowledge_add_node. 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.
9 tools across 3 categories: Execute, Read, Write. 5 are read-only. 4 can modify, create, or delete data.
One line change. Instead of running the Katashiro server directly, prefix it with Intercept: intercept -c katashiro.yaml -- npx -y @@nahisaho/katashiro-mcp-server. Download a pre-built policy from policylayer.com/policies/katashiro 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.