VerifiMind PEAS - RefleXion Trinity

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

X-Z-CS AI validation with auditable reasoning. 8 active tools; 5 in maintenance. v0.5.66

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "VerifiMind PEAS - RefleXion Trinity": {
      "url": "https://verifimind.ysenseai.org/mcp/",
      "transport": "streamable-http"
    }
  }
}

Measured tools (13)

• consult_agent_x

  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.

  Parameters:

  • concept_name (required) — string — Short name or title of the concept
  • concept_description (required) — string — Detailed description of the concept
  • detail — string
  • api_key — Optional API key for the provider (ephemeral, never stored)
  • context — Optional additional context or background
  • user_uuid
  • llm_provider — Optional LLM provider override ('groq', 'anthropic', 'openai', 'gemini', 'mistral', 'ollama', 'mock')

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• consult_agent_z

  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.

  Parameters:

  • concept_name (required) — string — Short name or title of the concept
  • concept_description (required) — string — Detailed description of the concept
  • detail — string
  • api_key — Optional API key for the provider (ephemeral, never stored)
  • context — Optional additional context or background
  • user_uuid
  • llm_provider — Optional LLM provider override ('groq', 'anthropic', 'openai', 'gemini', 'mistral', 'ollama', 'mock')
  • prior_reasoning — Optional reasoning from X agent to consider

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• consult_agent_cs

  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.

  Parameters:

  • concept_name (required) — string — Short name or title of the concept
  • concept_description (required) — string — Detailed description of the concept
  • detail — string
  • api_key — Optional API key for the provider (ephemeral, never stored)
  • context — Optional additional context or background
  • user_uuid
  • llm_provider — Optional LLM provider override ('groq', 'anthropic', 'openai', 'gemini', 'mistral', 'ollama', 'mock')
  • prior_reasoning — Optional reasoning from X and Z agents to consider

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• run_full_trinity

  Run complete X → Z → CS Trinity validation with Chain of Thought. This tool orchestrates all three agents in sequence: 1. X Intelligent analyzes innovation and strategy 2. Z Guardian reviews ethics (sees X's reasoning) 3. CS Security validates security (sees X and Z reasoning) 4. 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.

  Parameters:

  • concept_name (required) — string — Short name or title of the concept
  • concept_description (required) — string — Detailed description of the concept
  • detail — string — Reasoning verbosity (v0.5.44) — "standard" (default) returns the auditable `reasoning` block (per-step reasoning, ethics scoring breakdown + framework citations, Socratic questions, threat assessment) alongside the scores; "full" adds per-step evidence and the heaviest structured fields (12-dimension matrix, 6-stage record, MACP assessment); "summary" omits the reasoning block for the smallest payload. The block is additive — existing response fields are unchanged at every level.
  • api_key — Optional global API key for all agents (ephemeral, never stored)
  • context — Optional additional context or background
  • user_uuid
  • x_api_key — Optional API key override for X agent only
  • z_api_key — Optional API key override for Z agent only
  • cs_api_key — Optional API key override for CS agent only
  • x_provider — Optional provider override for X agent only
  • z_provider — Optional provider override for Z agent only
  • cs_provider — Optional provider override for CS agent only
  • llm_provider — Optional global LLM provider for all agents
  • save_to_history — boolean — Whether to save the full result to validation history (default: False). The store is shared and instance-local, retains at most the 20 newest opt-in results, evicts oldest entries on every read/write, and clears when the instance is replaced. It has no fixed time-retention guarantee. Leave False for private or sensitive concepts. During security maintenance a separately supplied user_uuid has no effect: no UUID-keyed validation history is written for it.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_prompt_templates

  List available prompt templates with optional filtering. v0.4.0 Unified Prompt Templates feature.

  Parameters:

  • tags — Comma-separated tags to filter by (e.g., 'genesis:phase-1,default')
  • agent_id — Filter by agent (X, Z, CS, or 'all')
  • category — Filter by category (startup, security, ethics, etc.)
  • user_uuid

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_prompt_template

  Get a specific prompt template by ID. v0.4.0 Unified Prompt Templates feature.

  Parameters:

  • template_id (required) — string — Unique template identifier
  • user_uuid
  • include_content — boolean — Whether to include full template content

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• export_prompt_template

  Export a prompt template to Markdown or JSON format. v0.4.0 Unified Prompt Templates feature.

  Parameters:

  • template_id (required) — string — Template to export
  • format — string — Export format ('markdown' or 'json')
  • user_uuid

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• register_custom_template

  Register a new custom prompt template. v0.4.0 Unified Prompt Templates feature.

  Parameters:

  • name (required) — string — Template display name
  • agent_id (required) — string — Target agent (X, Z, CS, or 'all')
  • content (required) — string — Template content with {variable} placeholders
  • tags — Comma-separated tags
  • category — string — Template category (default: 'custom')
  • user_uuid
  • description — Template description

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• import_template_from_url

  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

  Parameters:

  • url (required) — string — URL to import template from
  • validate — boolean — Whether to validate template content (default: True)
  • user_uuid

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_template_statistics

  Get statistics about the template registry. v0.4.0 Unified Prompt Templates feature. Returns: Statistics including template counts by agent, phase, and type

  Parameters:

  • user_uuid

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• coordination_handoff_create

  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. Returns: A COORDINATION_TEMPORARILY_DISABLED error with an incident reference.

  Parameters:

  • agent_id (required) — string
  • session_type (required) — string
  • completed (required) — array
  • decisions (required) — array
  • artifacts (required) — array
  • pending (required) — array
  • blockers (required) — array
  • next_agent
  • pioneer_key

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• coordination_handoff_read

  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. Returns: A COORDINATION_TEMPORARILY_DISABLED error with an incident reference.

  Parameters:

  • count — integer
  • agent_id
  • pioneer_key

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• coordination_team_status

  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. Returns: A COORDINATION_TEMPORARILY_DISABLED error with an incident reference.

  Parameters:

  • pioneer_key

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.