The GhostQA MCP server is primarily read-only, but rate limits are still recommended to control API costs and prevent retry loops.
Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.
These rules are based on the tool categories exposed by the GhostQA MCP server. Adjust the limits to match your use case.
Multi-platform:
rules:
- action: allow
rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
This is the complete policy file for GhostQA. It lists every tool with suggested default rules. Download it, adjust the limits, and run with Intercept.
version: "1" default: "deny" tools: Multi-platform: rules: - action: allow rate_limit: 60/minute Vision-powered: rules: - action: allow rate_limit: 60/minute YAML-configured: rules: - action: allow rate_limit: 60/minute
Download the policy
curl -o ghostqa.yaml https://raw.githubusercontent.com/policylayer/intercept/main/policies/ghostqa.yaml
Run Intercept in front of the server
intercept -c ghostqa.yaml -- npx -y @ghostqa
Works with any MCP client:
Every tool call is now checked against your policy before it reaches GhostQA. Denied calls are blocked and logged. Allowed calls pass through with no latency impact.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept