A
licenseA
qualityC
maintenanceRuntime policy enforcement for AI agents. Evaluate every agent action against your organization's policies before execution, with observe and enforce modes.
1
1
MIT
UNITARES
by cirwel
Related Servers
Alternatives to UNITARES
No user-submitted related servers found.
Related Servers
- FlicenseAqualityFmaintenanceProvides policy-based access control, incident tracking, and compliance monitoring to govern AI agent behavior. It enables organizations to enforce security rules and maintain audit trails by validating agent actions against trust levels and pattern-based policies.61-
Rigour MCPofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents to self-govern by scanning code for hardcoded secrets, structural violations, and AI drift in real-time, providing fix packets for automatic remediation.27MIT- AlicenseBqualityBmaintenanceProvides AI governance and action-assurance primitives, enabling trust scoring, policy-based allow/deny decisions, risk assessment, EU AI Act compliance checks, and an emergency kill-switch for autonomous agents.639 npmMIT
- AlicenseNot gradedqualityBmaintenanceBehavioral governance layer for AI assistants that monitors for hallucination, inconsistency, and unsafe reasoning patterns while managing stateful AI sessions.55 npmMIT
@vorionsys/mcp-serverofficial
AlicenseAqualityBmaintenanceMCP server for AI-agent governance using trust scoring, behavioral signals, and pre-flight action checks.1017 npm1Apache 2.0
TDQS
A4.1/5.0
Scored across 13 tools
Disambiguation3/5
Several tools overlap by design: sync_state and process_agent_update are 'canonical twins', start_session and onboard likewise, and check_working_state vs sync_state vs identity all touch governance state reads. The dense descriptions do disambiguate the intended path, but the twin/alias pattern and the list_tools/describe_tool/use_tool discovery layer duplicating the advertised surface create real misselection risk.
Naming Consistency4/5
Names are consistently snake_case, and most follow a verb_noun pattern (sync_state, check_working_state, search_shared_memory, store_finding, start_session, record_result, request_review, list_tools, describe_tool, use_tool). A few break the pattern (consult, identity, self_recovery) but remain readable and unambiguous in style.
Tool Count4/5
13 advertised tools is a well-scoped number for a governance server covering identity, state, memory, review, consultation, and recovery. However, the set is effectively larger since many capabilities (process_agent_update, onboard, outcome_event, update_finding, operator_resume_agent) are hidden behind use_tool, so the true surface is heavier than the count suggests.
Completeness4/5
The surface covers the lifecycle well: identity/session setup, state check-in and read, outcome recording, knowledge graph read/write, review, advisory consult, and self-recovery, plus a gateway to unlisted capabilities. Minor gaps remain (e.g., no explicit delete/archive for findings, revisions routed through the use_tool gateway), but core workflows are covered.
Maintenance
ActivityActive
ResponsivenessResponsive