VerifiMind PEAS - RefleXion Trinity

creator35lwb-web/verifimind-peas

Before you build a feature or product, run it through three specialized LLM agents that score innovation, ethics, and security in sequence. Each agent sees the prior reasoning. You get structured critique with PROCEED/REVISE/REJECT recommendations, not a formal proof. Ships 13 free tools: single-agent consult, full pipeline orchestration, template management for customizing the prompts, and MACP coordination handoffs if you're chaining multiple MCP servers. Supports seven LLM providers via BYOK. Works over streamable-http in Claude Desktop, Cursor, and VS Code. Rate limits are for system health, not paywalls. Think of it as productized multi-judge evaluation with an opinionated three-role specialization, exposed as MCP tools you can invoke mid-conversation.

GitHub stars: 2
tools: 13
transport: HTTP
last updated: Nov 6, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://verifimind.ysenseai.org/mcp/ --name verifimind-genesis

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http verifimind-genesis https://verifimind.ysenseai.org/mcp/

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 13 tools

Verified live against the running server on Nov 6, 2026.

consult_agent_xConsult 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_prov...7 params

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_prov...

Parameters* required

api_keyvalue

Optional API key for the provider (ephemeral, never stored)

concept_description*string

Detailed description of the concept

concept_name*string

Short name or title of the concept

contextvalue

Optional additional context or background

detailstring

default: standard

llm_providervalue

Optional LLM provider override ('groq', 'anthropic', 'openai', 'gemini', 'mistral', 'ollama', 'mock')

user_uuidvalue

consult_agent_zConsult 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...8 params

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...

Parameters* required

api_keyvalue

Optional API key for the provider (ephemeral, never stored)

concept_description*string

Detailed description of the concept

concept_name*string

Short name or title of the concept

contextvalue

Optional additional context or background

detailstring

default: standard

llm_providervalue

Optional LLM provider override ('groq', 'anthropic', 'openai', 'gemini', 'mistral', 'ollama', 'mock')

prior_reasoningvalue

Optional reasoning from X agent to consider

user_uuidvalue

consult_agent_csConsult 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...8 params

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...

Parameters* required

api_keyvalue

Optional API key for the provider (ephemeral, never stored)

concept_description*string

Detailed description of the concept

concept_name*string

Short name or title of the concept

contextvalue

Optional additional context or background

detailstring

default: standard

llm_providervalue

Optional LLM provider override ('groq', 'anthropic', 'openai', 'gemini', 'mistral', 'ollama', 'mock')

prior_reasoningvalue

Optional reasoning from X and Z agents to consider

user_uuidvalue

run_full_trinityRun 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)...14 params

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)...

Parameters* required

api_keyvalue

Optional global API key for all agents (ephemeral, never stored)

concept_description*string

Detailed description of the concept

concept_name*string

Short name or title of the concept

contextvalue

Optional additional context or background

cs_api_keyvalue

Optional API key override for CS agent only

cs_providervalue

Optional provider override for CS agent only

detailstring

Reasoning verbosity (v0.5.44) — "standard" (default) returns the auditable `reasoning` block (per-step reasoning, ethics scoring breakdown + framework citations, Socratic questions, threat assessme...default: standard

llm_providervalue

Optional global LLM provider for all agents

save_to_historyboolean

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/wri...default: false

user_uuidvalue

x_api_keyvalue

Optional API key override for X agent only

x_providervalue

Optional provider override for X agent only

z_api_keyvalue

Optional API key override for Z agent only

z_providervalue

Optional provider override for Z agent only

list_prompt_templatesList available prompt templates with optional filtering. v0.4.0 Unified Prompt Templates feature.4 params

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

Parameters* required

agent_idvalue

Filter by agent (X, Z, CS, or 'all')

categoryvalue

Filter by category (startup, security, ethics, etc.)

tagsvalue

Comma-separated tags to filter by (e.g., 'genesis:phase-1,default')

user_uuidvalue

get_prompt_templateGet a specific prompt template by ID. v0.4.0 Unified Prompt Templates feature.3 params

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

Parameters* required

include_contentboolean

Whether to include full template contentdefault: true

template_id*string

Unique template identifier

user_uuidvalue

export_prompt_templateExport a prompt template to Markdown or JSON format. v0.4.0 Unified Prompt Templates feature.3 params

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

Parameters* required

formatstring

Export format ('markdown' or 'json')default: markdown

template_id*string

Template to export

user_uuidvalue

register_custom_templateRegister a new custom prompt template. v0.4.0 Unified Prompt Templates feature.7 params

Parameters* required

agent_id*string

Target agent (X, Z, CS, or 'all')

categorystring

Template category (default: 'custom')default: custom

content*string

Template content with {variable} placeholders

descriptionvalue

Template description

name*string

Template display name

tagsvalue

Comma-separated tags

user_uuidvalue

import_template_from_urlImport 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 template3 params

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* required

url*string

URL to import template from

user_uuidvalue

validateboolean

Whether to validate template content (default: True)default: true

get_template_statisticsGet statistics about the template registry. v0.4.0 Unified Prompt Templates feature.1 params

Get statistics about the template registry. v0.4.0 Unified Prompt Templates feature.

Parameters* required

user_uuidvalue

coordination_handoff_createCreate 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 unauthent...9 params

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 unauthent...

Parameters* required

agent_id*string

artifacts*array

blockers*array

completed*array

decisions*array

next_agentvalue

pending*array

pioneer_keyvalue

session_type*string

coordination_handoff_readRead 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...3 params

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...

Parameters* required

agent_idvalue

countinteger

default: 1

pioneer_keyvalue

coordination_team_statusReturn 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 ti...1 params

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 ti...

Parameters* required

pioneer_keyvalue

Readme

VerifiMind PEAS

An opinionated MCP server for structured multi-LLM critique.

Three specialized agents — Innovation, Ethics, Security — review your concept before you build it. Multi-vendor (Gemini · Claude · GPT · Groq · Cerebras · Mistral · Ollama). Free, open-source, MCP-native.

View the full README on GitHub

Details

Repository: github.com/creator35lwb-web/verifimind-peas
Transport: HTTP
Registry: MCP registry, active
Resources: 4
Tools verified: Nov 6, 2026