What is a Role Brain?

A Role Brain is a persistent decision-pattern repository that captures the tacit knowledge and instincts of key personnel. When an executive departs, their Role Brain remains as a corporate asset, allowing a successor to operate at full capacity from Day 1.

How does StackFast differ from standard RAG implementations?

Standard RAG retrieves text without understanding context. StackFast provides a reasoning layer that applies judgment through structured logic, builds persistent Role Brains that compound over time, and enforces knowledge sovereignty through a 3-layer governance gate.

What is Knowledge Sovereignty?

Knowledge Sovereignty means your organization's intelligence never leaks into third-party training sets. Every brain entry is tagged for compliance and M&A readiness, with audit trails generated automatically for EU AI Act, SOC2, and HIPAA compliance.

How does StackFast reduce Key-Person Risk?

StackFast captures executive decision patterns, client relationship nuances, and institutional knowledge into structured Role Brains. When key personnel leave, their judgment and instincts remain as a corporate asset, reducing onboarding time for replacements and preserving institutional intelligence.

Back to Catalog

plugin

Agent Trust Router MCP

Agent Trust Router MCP is a ratified StackFast Store framework listing for Agent Trust Router.

Who it is for

Agents, operators, and CleverQ users that need a governed StackFast capability instead of a generic chat answer.

Problem it solves

Returns manifest-backed tool options, execution posture, trust reasons, and MASK/trace boundaries.

Activation model

Store discovery is catalog-ready. Execution posture: public-read-discovery+execute-after-auth-route. Public go-live remains gated until Robert ratifies publication.

Proof and source paths

Public job-name ratified 2026-05-27
Two-name doctrine applied
Proof-without-recipe disclosure boundary applied
Callable tools are real repo MCP tool IDs

Repo evidence

specs/CLEVERQ_FRAMEWORK_WORKBENCH_AND_AGENTIC_STORE_ADDENDUM_2026-05-27.md
specs/WO-CLEVERQ-FW-STORE-LISTINGS-P1-2026-05-27.md
lib/tool-registry/plugin-mcp-tools.ts
lib/framework-invocation/mcp-tools.ts

Capabilities

agent trust routing

mcp

A discovery and trust-routing tool that helps agents find allowed StackFast MCP capabilities. Returns manifest-backed tool options, execution posture, trust reasons, and MASK/trace boundaries.

Agent use
Use Agent Trust Router MCP through stackfast.framework.manifest, stackfast.framework.route, stackfast.framework.apply_mask, stackfast.framework.trace. Required boundaries: Public-read discovery with execute-after-auth routing for protected actions.. Do not request raw framework bodies or protected methodology.

Runtime registry status

Primary registry

stackfast.ai/api/mcp

Status

partial public mcp

Install gate

Catalog-ready only. Do not publish publicly until Robert ratifies store go-live.

Callable tools

stackfast.framework.manifest
stackfast.framework.route
stackfast.framework.apply_mask
stackfast.framework.trace

Missing or gated tools

No missing tools declared for the current V1 boundary.

Framework listing layer only; no parallel CleverQ engine introduced.
Public surfaces must render the human job-name and proof-without-recipe card fields.

Agent-readable queries

agent trust routerAI agent tool storewhich MCP plugin can this agent call safely?