MUJ428 Trust Layer — VERIFY BEFORE ACT for Grok
io.github.wmujahid428-web/trust-layer
MUJ428 verifies intent and evidence before consequential AI-agent actions.
client:Grok
transport:streamable-http
tools:14
Install MUJ428 Trust Layer — VERIFY BEFORE ACT in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"trust-layer": {
"type": "http",
"url": "https://wepmhfjzckclvywolrek.supabase.co/functions/v1/trust-layer-mcp"
}
}
}Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs
What Grok can do once it is connected
- rescue_agent_before_consequence
- trust_action
- invoke_trust_service
- get_service_catalog
- get_payment_rails
- resolve_trust_route
- get_trust_heartbeat
- find_trust_capabilities
- publish_trust_request
- observe_trust_compatibility
- select_payment_rail
- get_trust_layer_pricing
- select_assurance_tier
- get_capabilities