HANRIA agent mandate check
Server Details
Check an agent action against its operator's mandate before acting: permit, deny or escalate.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
check_action and validate_mandate have clearly distinct purposes: one evaluates a runtime action against a mandate, the other validates the mandate itself before use. The descriptions explicitly state when to call each, eliminating ambiguity.
Both tools follow a consistent verb_noun snake_case pattern (check_action, validate_mandate), making the surface predictable and easy to scan.
Two tools is slightly below the typical 3-15 range, but for a narrowly scoped mandate-checking server each tool serves a distinct essential function (runtime check vs. mandate validation). The set does not feel bloated or arbitrary.
The domain is agent mandate checking, and the surface covers both key workflows: validating a mandate before reliance and checking actions against a mandate at runtime. No obvious gaps exist for the stated purpose; receipts and reasons are returned by check_action.
Available Tools
2 toolscheck_actionCheck an agent action against a mandateARead-onlyIdempotentInspect
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
Inputs: action (required), mandate (required). Returns: clause, reason, outcome, receipt, +4 more
validate_mandateCheck a mandate for errorsARead-onlyIdempotentInspect
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
Inputs: mandate (required). Returns: valid, reason, clauses, expired, +3 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Check a proposed agent action against operator's rules: permit, deny or escalate, with the clause.
Deterministic allow/require_approval/deny verdicts for agent actions, before they happen.
EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.
Pre-execution policy gate for consequential agent actions with durable trust receipts.
Related MCP Servers
- AlicenseAqualityBmaintenanceVerifies agent actions against mandates via a single tool, returning allow, deny, or requires_approval receipts without executing the actions.149 npmMIT
- AlicenseNot gradedqualityBmaintenanceContinuous mandate enforcement for AI agents: block an action a signed mandate does not permit — amount, payee, audience, expiry — and name the rule that fired. Verdicts are Ed25519-signed and verify offline.Apache 2.0
- AlicenseAqualityDmaintenanceEnables agents to request payment authorization against signed human mandates, enforcing policy-as-code limits and returning a decision (authorize, challenge, or deny) without moving funds.11Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnforces configurable policies on AI agent tool calls, allowing, requesting review, or denying actions before they are executed.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.