# HANRIA agent mandate check

> HANRIA agent mandate check is a free MCP server for security. Check an agent's proposed action against its operator's mandate: permit, deny or escalate. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** API, Web
- **Website:** https://hanria.ai
- **MCP Registry name:** ai.hanria/agent-mandate-check
- **Categories:** security, developer tools
- **Listing updated:** 2026-11-16

## About

A mandate is a file the operator owns, naming what an agent may do, what is denied and what must go to a person. This hosted check evaluates a proposed action against it and answers permit, deny or escalate with the clause named. Answers carry a receipt signed with HANRIA's published key, bound to digests of the exact mandate and action and to a 15-minute window. The receipt proves what the check answered, not that the action happened.

The service keeps no request content. The same evaluator also ships as a local skill under the MIT licence, with Python standard library only, no network and no account, which logs each decision to disk.

HANRIA places this inside a wider design for agent commerce: continuity, authority, liability and portable evidence, plus independent review before payment. It is candid about limits: a skill can advise, but only a runtime that exclusively controls the tools or credentials can actually refuse.

## Features

- **Three outcomes:** Permit, deny or escalate, naming the clause.
- **Signed receipts:** Bound to the mandate, action and a 15-minute window.
- **No content kept:** The hosted check stores no request content.
- **Local version:** MIT Python skill with no network.
- **Hash-chained log:** Decisions are appended to an on-disk record.
- **Fail-closed model:** Checks run in order and fail closed.

## Good for

- Gate an agent's payment before it executes
- Escalate high-risk actions to a human
- Keep an audit trail of agent decisions
- Verify a receipt for a past decision
- Define what a purchasing agent may do

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http agent-mandate-check https://check.hanria.ai/v1/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://check.hanria.ai/v1/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "agent-mandate-check": {
      "url": "https://check.hanria.ai/v1/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

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

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "agent-mandate-check": {
      "serverUrl": "https://check.hanria.ai/v1/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

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

## FAQ

### Is the hosted check free?

The site says it is offered free.

### Does the receipt prove the action happened?

No, only what the check answered.

### Can it block an agent?

Only a runtime that controls the tools can; the check advises.

### What endpoints exist?

MCP at check.hanria.ai/v1/mcp and HTTP at /v1/check.

### Is HANRIA agent mandate check free?

Yes. HANRIA agent mandate check is free to use.

### How do I add HANRIA agent mandate check to Claude Code?

Run this command in your terminal: claude mcp add --transport http agent-mandate-check https://check.hanria.ai/v1/mcp

### What are the best alternatives to HANRIA agent mandate check?

The closest alternatives to HANRIA agent mandate check are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/hanria-agent-mandate-check
