HANRIA agent mandate check
ai.hanria/agent-mandate-checkCheck an agent action against its operator's mandate before acting: permit, deny or escalate.
Score: 100/100
Handshake verified by our own probe.
Tools · 2
Call this before your agent does something consequential (sends, pays, deletes, publishes, installs or changes access). Pass mandate (the operator's rules; the first matching clause decides) and actio…
Call this after writing or editing a mandate, before relying on it. Returns valid true or false with the reason: schema errors, clauses that can never run because an earlier clause already decides the…
Resources · 5
Permit bounded on-chain transfers to named recipients and escalate everything else.
hanria://mandates/payments-ceiling
Deny sensitive directories and permit reads and writes under one bounded directory.
hanria://mandates/file-sandbox
Permit network posts only to one mail API prefix.
hanria://mandates/outbound-email
Escalate administrative deploys to a person.
hanria://mandates/deploy-gate
Permit network gets to HTTPS targets and deny every other action.
hanria://mandates/read-only-research
Prompts · 1
Write a mandate from the closest validated HANRIA template.
How to use
Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://check.hanria.ai/v1/mcp
Cursor or Cline: add to your MCP config:
{
"mcpServers": {
"hanria_agent_mandate_check": {
"url": "https://check.hanria.ai/v1/mcp",
"transport": "streamable-http"
}
}
}