6 tools. 1 can modify or destroy data without limits.
1 write tool that can modify data. Rate limits recommended.
Last updated:
Execute tools (ingest) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
Intercept sits between your agent and Human State. 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 @nefesh-ai/human-state check_api_key_status:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
The Human State server is primarily read-only with 5 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.
6 tools across 2 categories: Execute, Read. 5 are read-only. 1 can modify, create, or delete data.
One line change. Instead of running the Human State server directly, prefix it with Intercept: intercept -c nefesh-ai-human-state.yaml -- npx -y @nefesh-ai/human-state. Download a pre-built policy from policylayer.com/policies/nefesh-ai-human-state 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