VerifiMind PEAS - RefleXion Trinity
Server Details
X-Z-CS AI validation with auditable reasoning. 8 active tools; 5 in maintenance. v0.5.68
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- creator35lwb-web/VerifiMind-PEAS
- GitHub Stars
- 2
- Server Listing
- VerifiMind PEAS
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 13 tools
The three consult_agent_* tools are clearly differentiated by persona (CS security, X innovation, Z ethics), but run_full_trinity overlaps heavily with them, differing only in orchestration scope. The six template tools include near-neighbors like get_prompt_template vs export_prompt_template, and the three coordination_* tools are functionally identical in that all simply return a denial.
Most tools follow verb_noun (get_prompt_template, list_prompt_templates, register_custom_template), but the coordination tools invert the pattern (coordination_handoff_create, coordination_team_status) and the template noun alternates between 'template' and 'prompt_template'. Readable overall, but no single predictable convention.
13 tools is a reasonable size for a validation-plus-template-registry server, and each template tool maps to a distinct operation. However, three of the thirteen are permanently disabled no-ops, so the effective working surface is smaller than advertised.
The prompt-template registry covers list/get/register/import/export/stats but has no update or delete, leaving a lifecycle gap. More significantly, the entire coordination subsystem (create/read/status) is contained and non-functional, which removes a stated capability from the surface with no alternative provided.
Available Tools
13 toolsconsult_agent_csConsult Agent CsAInspect
Consult CS Security agent for security validation and Socratic interrogation.
CS Security specializes in:
Security vulnerability assessment
Attack vector identification
Data security review
System integrity analysis
Socratic questioning (challenging assumptions)
BYOK (v0.4.5): Pass llm_provider and api_key to use your own LLM. If only api_key is provided, the provider is auto-detected from the key prefix. Keys are ephemeral (never stored) and garbage collected after the call.
Inputs: concept_name (required), concept_description (required), detail, api_key, +4 more. Returns: object
consult_agent_xConsult Agent XAInspect
Consult X Intelligent agent for innovation and strategy analysis.
X Intelligent specializes in:
Innovation potential assessment
Strategic value analysis
Market opportunity identification
Competitive positioning
Growth potential evaluation
BYOK (v0.4.5): Pass llm_provider and api_key to use your own LLM. If only api_key is provided, the provider is auto-detected from the key prefix. Keys are ephemeral (never stored) and garbage collected after the call.
Inputs: concept_name (required), concept_description (required), detail, api_key, +3 more. Returns: object
consult_agent_zConsult Agent ZAInspect
Consult Z Guardian agent for ethical review and Z-Protocol enforcement.
Z Guardian specializes in:
Ethical implications assessment
Privacy and data protection review
Bias and fairness analysis
Social impact evaluation
Z-Protocol compliance verification
Z Guardian has VETO POWER. If veto_triggered is True, the concept should not proceed as it crosses ethical red lines.
BYOK (v0.4.5): Pass llm_provider and api_key to use your own LLM. If only api_key is provided, the provider is auto-detected from the key prefix. Keys are ephemeral (never stored) and garbage collected after the call.
Inputs: concept_name (required), concept_description (required), detail, api_key, +4 more. Returns: object
coordination_handoff_createCoordination Handoff CreateAInspect
Create a structured MACP v2.5 handoff record.
TEMPORARILY DISABLED — this tool is contained pending a security repair (incident VM-IR-2026-07-28-COORD-01) and always returns a denial.
Handoff bodies written through this tool were stored in a shared namespace that any unauthenticated caller could read. Nothing is stored or returned while containment is in force. Coordination state belongs in your own repository until private, owner-scoped storage ships.
All arguments are accepted for schema stability and are ignored; no supplied value is stored, logged, or echoed back.
Inputs: pending (required), agent_id (required), blockers (required), artifacts (required), +5 more. Returns: object
coordination_handoff_readCoordination Handoff ReadAInspect
Read the most recent coordination handoff record(s).
TEMPORARILY DISABLED — this tool is contained pending a security repair (incident VM-IR-2026-07-28-COORD-01) and always returns a denial.
This read path returned complete handoff bodies from a caller-selected namespace with no authenticated ownership check. It is closed to every caller — with or without a key — while owner-scoped access control is rebuilt. No record body is returned.
All arguments are accepted for schema stability and are ignored.
Inputs: count, agent_id, pioneer_key. Returns: object
coordination_team_statusCoordination Team StatusAInspect
Return current team coordination state and session summary.
TEMPORARILY DISABLED — this tool is contained pending a security repair (incident VM-IR-2026-07-28-COORD-01) and always returns a denial.
This summary exposed agent identities, pending actions, open blockers, and a timestamped activity index from a caller-selected namespace with no authenticated ownership check — enough to enumerate a namespace before reading it. It is closed to every caller while owner-scoped access control is rebuilt.
All arguments are accepted for schema stability and are ignored.
Inputs: pioneer_key. Returns: object
export_prompt_templateExport Prompt TemplateCInspect
Export a prompt template to Markdown or JSON format.
v0.4.0 Unified Prompt Templates feature.
Inputs: template_id (required), format, user_uuid. Returns: object
get_prompt_templateGet Prompt TemplateCInspect
Get a specific prompt template by ID.
v0.4.0 Unified Prompt Templates feature.
Inputs: template_id (required), user_uuid, include_content. Returns: object
get_template_statisticsGet Template StatisticsCInspect
Get statistics about the template registry.
v0.4.0 Unified Prompt Templates feature.
Inputs: user_uuid. Returns: object
import_template_from_urlImport Template From UrlBInspect
Import a prompt template from a URL (GitHub Gist, raw file, etc.).
v0.4.0 Unified Prompt Templates feature.
Supports:
GitHub Gist URLs
Raw GitHub file URLs
Any HTTPS URL pointing to JSON/YAML template
Inputs: url (required), validate, user_uuid. Returns: object
list_prompt_templatesList Prompt TemplatesBInspect
List available prompt templates with optional filtering.
v0.4.0 Unified Prompt Templates feature.
Inputs: tags, agent_id, category, user_uuid. Returns: object
register_custom_templateRegister Custom TemplateCInspect
Register a new custom prompt template.
v0.4.0 Unified Prompt Templates feature.
Inputs: name (required), content (required), agent_id (required), tags, +3 more. Returns: object
run_full_trinityRun Full TrinityAInspect
Run complete X → Z → CS Trinity validation with Chain of Thought.
This tool orchestrates all three agents in sequence:
X Intelligent analyzes innovation and strategy
Z Guardian reviews ethics (sees X's reasoning)
CS Security validates security (sees X and Z reasoning)
Results are synthesized into a unified assessment
Each agent sees the reasoning of previous agents, enabling true collaborative analysis with full transparency.
BYOK (v0.4.5): Pass llm_provider/api_key for all agents, or use per-agent overrides (x_provider/x_api_key, z_provider/z_api_key, cs_provider/cs_api_key). Per-agent params take priority over global. Keys are ephemeral (never stored) and garbage collected after the call.
Inputs: concept_name (required), concept_description (required), detail, api_key, +10 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Read-only search of 2,189 AI agent tools (MCP servers, x402 APIs) with daily automated trust scores.
15 deterministic validation tools for AI agents: tax IDs (15 countries), VAT, IBAN, LEI, HS codes.
Eight metered machine-intelligence tools for AI agents with native x402 payment paths.
AI-operated. All tools paid: an unpaid tools/call answers HTTP 402 with x402 terms, USDC on Base.
Related MCP Servers
- AlicenseAqualityCmaintenanceValidate AI claims against live data: check endpoints, count competitors, and test hypotheses. Includes free and paid tools via x402.16MIT

dynamicfeed-mcpofficial
AlicenseNot gradedqualityDmaintenance62 live, cryptographically signed data tools for AI agents and robots: weather, natural hazards, flights, shipping, space, CVEs, sanctions, software versions, sea ice and more. Every datapoint carries source, licence, timestamp and an Ed25519 signature.17 npmMIT- AlicenseNot gradedqualityBmaintenanceCryptographic AI governance and compliance attestation. 75 tools across 80 regulatory frameworks including EU AI Act, NIST AI RMF, NERC CIP, 3GPP R19, OWASP MCP Top 10, CMMC, and SR 11-7. Full OWASP MCP Top 10 coverage. Witness Middleware for zero-code transport-layer compliance. Runtime containment attestation. Distillation provenance. Incident lifecycle chains.524 npmApache 2.0
- AlicenseAqualityDmaintenancePolicy-gated MCP execution for AI agents—ShadeGuard, x402, signed receipts, no custody. 16 tools, 18 chains.182MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.