HANRIA agent mandate check

ai.hanriaPublished by hanria.aiOfficial publisherv0.7.4Updated Oct 24, 2026

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

The publisher's own server: Check

VerifiedStreamable HTTPWeb executableProductivity & WorkflowSecurity & Monitoring

Overview

AI-generated overview

A remote MCP server that checks a proposed agent action against the operator's mandate and returns permit, deny or escalate before the action runs.

What you can do
Check a proposed action against a mandate and get permit, deny or escalate with a reason, passing the mandate, action kind, verb, target, optional counterparty and amount. Validate a written or edited mandate for schema errors, unreachable clauses, unbounded prefixes, credential material and expiry before relying on it.
When to use it
Use it when an assistant or agent is about to do something consequential such as sending, paying, deleting, publishing, installing or changing access, and you want a policy decision recorded first. Also useful after editing a mandate to confirm it is valid before checks depend on it.
Requirements
A remote streamable HTTP endpoint at check.hanria.ai; no authentication, environment variables or headers are declared. The assistant must supply the mandate text and the action details with each call.
Before you install
The mandate is sent to a third-party service on every check, so avoid embedding secrets in it; the validator flags credential material. A permit is advisory only and does not itself perform or block the action, so the agent must still enforce the decision. An invalid mandate makes every check unreliable.

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.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.hanria%2Fagent-mandate-check/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

Tools

2

check_action

Check an agent action against a mandate

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 action (kind, verb, target, optional counterparty and amount). Returns permit, deny or escalate with the governing clause, a reason, an action digest and a signed receipt; treat error as deny. Advisory: it cannot stop an action, and it keeps no request content. To check a new mandate first, call validate_mandate. Examples: inputSchema. Docs: https://hanria.ai/llms.txt

Parametersactionrequiredmandaterequired

validate_mandate

Check a mandate for errors

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 them, unbounded prefixes, credential material, and expiry. An invalid mandate makes every check_action call answer error. Once per mandate version is enough; there is no need to call it before every check_action. Free, and it keeps no request content. Docs: https://hanria.ai/llms.txt

Parametersmandaterequired

Version history

8
  1. v0.7.4LatestOct 10, 2026
  2. v0.7.3Oct 10, 2026
  3. v0.7.1Oct 9, 2026
  4. v0.6.1Oct 8, 2026
  5. v0.6.0Oct 3, 2026
  6. v0.5.0Oct 2, 2026
  7. v0.4.0Oct 2, 2026
  8. v0.3.0Sep 30, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Hanria integrations

Check

ai.hanriaOfficial publisher

A remote MCP server that checks a proposed agent action against the operator's mandate and returns permit, deny or escalate with the deciding clause.

Streamable HTTPWeb executable
Productivity & Workflow2 toolsOct 24, 2026