HANRIA agent mandate check

ai.hanriav0.3.0Updated Sep 30, 2026

Check an agent action against its operator's mandate before acting: permit, deny or escalate.

VerifiedStreamable HTTPWeb executableSecurity & Monitoring

Overview

AI-generated overview

A remote MCP endpoint that checks a proposed agent action against its operator's mandate and returns permit, deny, or escalate.

What it does
This server exposes a single decision point for agent actions: given a proposed action, it evaluates it against the operator's mandate and returns one of three outcomes — permit, deny, or escalate. It is a remote streamable HTTP endpoint, so the assistant calls it over the network rather than running it locally. No tools, packages, environment variables, or headers are declared in the manifest.
When to use it
Worth adding when an assistant takes consequential actions on someone's behalf and you want a mandate check before acting, especially where a human should be asked to confirm borderline cases. It is a gate, not a general-purpose tool, so it only helps if your workflow can pause on a deny or escalate result.
Requirements
A remote MCP client that supports streamable HTTP, pointed at the provider's hosted endpoint. No authentication, environment variables, or headers are declared, and no local runtime or package is needed.
Before you install
The manifest declares no authentication, so consider what action details you send to a third-party endpoint and whether that is acceptable for your data. The check itself is advisory: it does not enforce anything unless your workflow actually honors a deny or escalate result. No credentials, payments, or write operations are shown in the input.

Installation

In SourceWeft

  1. Open HANRIA agent mandate check in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agent-mandate-check": {
      "type": "http",
      "url": "https://check.hanria.ai/v1/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.3.0LatestSep 30, 2026