5 tools. 1 can modify or destroy data without limits.
1 write tool that can modify data. Rate limits recommended.
Last updated:
Execute tools (diagnose) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
Intercept sits between your agent and Ask Llm. 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 @ask-llm-mcp ask-llm:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
The Ask Llm server is primarily read-only with 4 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.
5 tools across 2 categories: Execute, Read. 4 are read-only. 1 can modify, create, or delete data.
One line change. Instead of running the Ask Llm server directly, prefix it with Intercept: intercept -c io-github-lykhoyda-ask-llm.yaml -- npx -y @ask-llm-mcp. Download a pre-built policy from policylayer.com/policies/io-github-lykhoyda-ask-llm 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