Verax
OfficialRelated Servers
Alternatives to Verax
- AlicenseAqualityCmaintenanceSelf-hosted governance layer between an AI assistant and your data: allow/deny policy, deterministic PII masking, row caps, and a hash-chained audit log with an Ed25519-signed receipt for every access, verifiable offline.4101 npm3MIT
- AlicenseAqualityAmaintenancePolicy-gated agent spend with signed receipts and rail-extract audit: a fail-closed gate issues a COSE receipt for every allowed payment, and the audit reconciles those receipts against a rail extract so a settlement with no receipt is named rather than assumed. It settles on a mock rail, holding no wallet and signing no transaction.51Apache 2.0
- AlicenseAqualityBmaintenanceEnables AI agents to store and retrieve provenance-aware facts with source, age, and boundaries, supporting search, read, propose, and local telemetry via MCP tools.456 npmApache 2.0
Related Servers
- AlicenseNot gradedqualityBmaintenanceProvides a governed execution boundary for AI agents, enforcing deterministic policy, one-shot human approvals, and signed receipts for MCP tool effects.MIT
- AlicenseNot gradedqualityBmaintenanceProvides a policy-controlled MCP gateway that lets agents invoke tools with explicit policies, bounded execution, scoped visibility, and decision receipts.MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to safely call MCP tools through a security gateway that enforces per-role authorization and least-privilege tool scoping.1-
- AlicenseNot gradedqualityCmaintenanceEnables LLM agents to safely invoke enterprise MCP tools under an enforceable guard that applies allowlist policies, caller roles, parameter restrictions, human confirmation for destructive operations, and a correlated JSONL audit log.AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to govern downstream tool servers by enforcing default-deny authority and attestation on every tool call, with live monitoring, approval, and mid-session revocation.3Apache 2.0
- FlicenseNot gradedqualityBmaintenanceProvides a secure MCP boundary for AI agents, intercepting and validating tool calls, redacting secrets, and requiring human approval for sensitive actions with a tamper-evident audit trail.-
TDQS
Scored across 6 tools
Each tool has a clear, distinct purpose: memory.get/put for storage, audit.explain for decision lookup, message.read/send for messaging, and spend for payment authorization. There is no overlap or ambiguity; an agent can confidently select the right tool for a task.
Most tools follow a consistent 'domain.verb' pattern (memory.get, memory.put, audit.explain, message.read, message.send), but 'spend' is a lone verb without a domain prefix, creating a minor deviation. The overall style is uniform and readable.
With 6 tools, the surface is well-scoped for the domains covered (memory, messaging, audit, spending). Each tool serves a distinct operational need, and the count is neither sparse nor bloated.
Core operations are covered: memory supports get and put (including replace), messaging supports read and send, audit supports explain (though no list), and spend supports authorization. Minor gaps exist, such as no explicit delete for memory or messages and no audit listing, but these are not critical for the intended workflows.