Skip to main content
Glama

VerifiMind PEAS - RefleXion Trinity

by io.github.creator35lwb-web
OverviewDiscussionsAdmin

Run Full Trinity

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
detailNoReasoning 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.standard
api_keyNoOptional global API key for all agents (ephemeral, never stored)
contextNoOptional additional context or background
user_uuidNo
x_api_keyNoOptional API key override for X agent only
z_api_keyNoOptional API key override for Z agent only
cs_api_keyNoOptional API key override for CS agent only
x_providerNoOptional provider override for X agent only
z_providerNoOptional provider override for Z agent only
cs_providerNoOptional provider override for CS agent only
concept_nameYesShort name or title of the concept
llm_providerNoOptional global LLM provider for all agents
save_to_historyNoWhether 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.
concept_descriptionYesDetailed description of the concept

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / save_to_history / description
      Previous value: -"Whether to save the full result to validation history\n(default: False). The store is shared and instance-local, retains at\nmost the 20 newest opt-in results, evicts oldest entries on every\nread/write, and clears when the instance is replaced. It has no fixed\ntime-retention guarantee. Leave False for private or sensitive concepts.\nIf user_uuid is supplied separately, pseudonymous validation metadata\nmay still be written to UUID-keyed Firestore history (see Privacy v2.5)."New value: +"Whether to save the full result to validation history\n(default: False). The store is shared and instance-local, retains at\nmost the 20 newest opt-in results, evicts oldest entries on every\nread/write, and clears when the instance is replaced. It has no fixed\ntime-retention guarantee. Leave False for private or sensitive concepts.\nDuring security maintenance a separately supplied user_uuid has no\neffect: no UUID-keyed validation history is written for it."
  2. Changed1 schema field changed
    • changedInput schema / properties / save_to_history / description
      Previous value: -"Whether to save result to validation history (default: False).\nHistory is a single shared store on this server instance; leaving this\nFalse prevents the full concept/result from being written there. If\nuser_uuid is supplied separately, pseudonymous validation metadata may\nstill be written to UUID-keyed Firestore history (see Privacy v2.4)."New value: +"Whether to save the full result to validation history\n(default: False). The store is shared and instance-local, retains at\nmost the 20 newest opt-in results, evicts oldest entries on every\nread/write, and clears when the instance is replaced. It has no fixed\ntime-retention guarantee. Leave False for private or sensitive concepts.\nIf user_uuid is supplied separately, pseudonymous validation metadata\nmay still be written to UUID-keyed Firestore history (see Privacy v2.5)."
  3. Changed1 schema field changed
    • changedInput schema / properties / save_to_history / description
      Previous value: -"Whether to save result to validation history (default: False).\nHistory is a single shared store on this server instance; leaving this\nFalse keeps your concept private to your own call (v0.5.43 privacy fix)."New value: +"Whether to save result to validation history (default: False).\nHistory is a single shared store on this server instance; leaving this\nFalse prevents the full concept/result from being written there. If\nuser_uuid is supplied separately, pseudonymous validation metadata may\nstill be written to UUID-keyed Firestore history (see Privacy v2.4)."
  4. First observed

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It discloses the sequential flow, the fact that each agent sees previous reasoning, and the ephemeral nature of keys. The save_to_history parameter is well-documented in the schema, and the description adds clarity on storage limits and privacy considerations, which is valuable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear enumeration of steps and a separate paragraph for BYOK details. It front-loads the core purpose, then details the orchestration, and finally addresses key usage details. It is slightly longer than necessary but each sentence contributes to understanding the tool's behavior and key nuances.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multi-agent orchestration, 14 parameters, output schema present), the description is quite complete. It explains the flow, transparency, and key parameter behaviors. However, it could optionally mention what the unified assessment looks like or any prerequisites, but the output schema likely covers return values. Overall, it is adequate for an agent to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is high (93%), so the baseline is 3. The description adds context for the BYOK parameters (priority rules, ephemeral handling) and mentions the detail parameter's behavior, but does not elaborate on every parameter. The schema descriptions already provide sufficient meaning for most parameters, so the description adds marginal value beyond that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: running a complete three-agent validation (X, Z, CS) with Chain of Thought, and orchestrates all three agents in sequence. It distinguishes itself from sibling tools like consult_agent_x/z/cs by emphasizing the full pipeline and the reasoning transparency between agents.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the orchestration flow and the BYOK details, including priority rules and ephemeral key handling. However, it does not explicitly state when to use this tool versus the single-agent consult tools, leaving that inference to the agent. It could have mentioned that for single-agent consultations, one should use consult_agent_x/z/cs instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All VerifiMind PEAS - RefleXion Trinity toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources