HANRIA agent mandate check

by hanria.ai · remote · no sign-in to list tools · v0.7.4 · published by ai.hanria

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

Changes · 2

Compare Registry entry

2 tools: 2 change things.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things2Claude Code: ask: see these tools
Only reads0Claude Code: allow

10 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Findings

Matches of fixed checks, with the text they matched.

2 warn8 info

Warncheck_action
The server marks "check_action" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "call": a word for a change.
What this check looks for
Warnvalidate_mandate
The server marks "validate_mandate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The name "validate_mandate" says "validate": a word for reading.
What this check looks for
Infocheck_action
The input schema at properties.mandate.description mentions "credentials".
Matched text
inputSchema.properties.mandate.description: "...a component that exclusively holds the credentials and can refuse."
What this check looks for
Infocheck_action
The input schema at properties.mandate.$comment mentions "credential".
Matched text
inputSchema.properties.mandate.$comment: "...s of doing it, and must never contain a credential, secret, key or token. The checker refu..."
What this check looks for
Infocheck_action
The input schema at properties.action.description mentions "credentials".
Matched text
inputSchema.properties.action.description: "...local HANRIA runtime. MUST NOT contain credentials, secrets, private keys, or tokens."
What this check looks for
Infocheck_action
The input schema at properties.action.properties.operation.properties.parameters.description mentions "credential".
Matched text
inputSchema.properties.action.properties.operation.properties.parameters.description: "...st whose parameters appear to contain a credential."
What this check looks for

Show 4 more findings

Infocheck_action
The input schema at properties.action.$comment mentions "credential".
Matched text
inputSchema.properties.action.$comment: "Forbidden anywhere in an instance: credential, secret, private_key, token, password,..."
What this check looks for
Infovalidate_mandate
The description mentions "credential".
Matched text
description: "...ready decides them, unbounded prefixes, credential material, and expiry. An invalid mandat..."
What this check looks for
Infovalidate_mandate
The input schema at properties.mandate.description mentions "credentials".
Matched text
inputSchema.properties.mandate.description: "...a component that exclusively holds the credentials and can refuse."
What this check looks for
Infovalidate_mandate
The input schema at properties.mandate.$comment mentions "credential".
Matched text
inputSchema.properties.mandate.$comment: "...s of doing it, and must never contain a credential, secret, key or token. The checker refu..."
What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Changes things 2Creates or changes something that can be changed back.Claude Code: ask

check_actionCall this before your agent does something consequential (sends, pays, deletes, publishes, installs or changes access).6 findings
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
  The input schema at properties.mandate.description mentions "credentials".
  Matched text
  inputSchema.properties.mandate.description: "...a component that exclusively holds the credentials and can refuse."
  What this check looks for
- Info
  The input schema at properties.mandate.$comment mentions "credential".
  Matched text
  inputSchema.properties.mandate.$comment: "...s of doing it, and must never contain a credential, secret, key or token. The checker refu..."
  What this check looks for
- Info
  The input schema at properties.action.description mentions "credentials".
  Matched text
  inputSchema.properties.action.description: "...local HANRIA runtime. MUST NOT contain credentials, secrets, private keys, or tokens."
  What this check looks for
- Info
  The input schema at properties.action.properties.operation.properties.parameters.description mentions "credential".
  Matched text
  inputSchema.properties.action.properties.operation.properties.parameters.description: "...st whose parameters appear to contain a credential."
  What this check looks for
- Info
  The input schema at properties.action.$comment mentions "credential".
  Matched text
  inputSchema.properties.action.$comment: "Forbidden anywhere in an instance: credential, secret, private_key, token, password,..."
  What this check looks for
- Warn
  The server marks "check_action" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "call": a word for a change.
  What this check looks for
Description, as the server wrote it
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
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
validate_mandateCall this after writing or editing a mandate, before relying on it.4 findings
Why it is in this group
- The name "validate_mandate" says "validate": a word for reading.
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
  The description mentions "credential".
  Matched text
  description: "...ready decides them, unbounded prefixes, credential material, and expiry. An invalid mandat..."
  What this check looks for
- Info
  The input schema at properties.mandate.description mentions "credentials".
  Matched text
  inputSchema.properties.mandate.description: "...a component that exclusively holds the credentials and can refuse."
  What this check looks for
- Info
  The input schema at properties.mandate.$comment mentions "credential".
  Matched text
  inputSchema.properties.mandate.$comment: "...s of doing it, and must never contain a credential, secret, key or token. The checker refu..."
  What this check looks for
- Warn
  The server marks "validate_mandate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The name "validate_mandate" says "validate": a word for reading.
  What this check looks for
Description, as the server wrote it
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
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.7.4. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__agent-mandate-check__check_action",
      "mcp__agent-mandate-check__validate_mandate"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agent-mandate-check. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/ai.hanria/agent-mandate-check/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

2 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 17:41 UTC.

For agents: Markdown · JSON · report this listing