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

StackFast Governed Decision MCP

StackFast Governed Decision MCP exposes the public decision-support surface behind `stackfast.think.decide`, giving approved agents a bounded way to ask complex questions, evaluate artifacts, and produce evidence-aware decision packets without exposing protected internal reasoning names.

Host and data posture

Where this product is meant to live.

Decision receipt product with public proof potential and operator review depth.

Commercial shape

Public-app proof

Data posture

Tenant brain optional

Approval posture

Approval required

Best demo

ChatGPT / Claude.ai / Grok

Best daily use

StackFast UI

Who it is for

Agent builders, executives, operators, advisors, and enterprise teams that need traceable decision support rather than generic chat answers.

Problem it solves

It turns open-ended strategic, operational, technical, or artifact-review questions into structured options, gaps, hidden factors, confidence notes, and review boundaries that a human can inspect before acting.

Activation model

Assisted install through the StackFast MCP control plane with wallet authentication, tenant scope, MASK policy, bounded reasoning budget, and human review for high-impact recommendations.

Proof and source paths

stackfast.think.decide tool-registry seed exists
Governed Decision MCP manual exists for agent retrieval
Decision-support MCP spec exists
Deep-analysis specs exist internally; public output remains masked
Website MCP host exposes the decision tool through the shared control plane

Repo evidence

docs/wiki-manuals/stackfast-governed-decision-mcp-manual.md
lib/think-decision/mcp-tool.ts
lib/tool-registry/plugin-mcp-tools.ts
app/api/mcp/route.ts

Capabilities

governed decision analysis

mcp

Analyze a question, artifact, or decision packet and return decision options, gaps, confidence notes, and review boundaries.

Agent use
Calls stackfast.think.decide through the StackFast MCP control plane to run bounded governed decision analysis over a question, artifact, or decision packet. Use for traceable non-autonomous decision support with evidence pointers, candidate options, gaps, confidence notes, and render-boundary metadata.

Connector proof

Catalog is not the same as customer-ready.

This product only becomes market-ready after a real host mounts the entitled tools, a safe call succeeds, metering records the event, and a customer-safe receipt exists. Until then, the page shows the strongest proven status without rounding up.

Catalog

Runtime registry and product manifest are present.

Entitlement

Execution requires OAuth or storefront entitlement scope.

Callable

Callable tool proof is incomplete.

Metering

Metering waits on callable execution.

Customer validated

Pending fresh host-surface call receipt.

Runtime registry status

Primary registry

stackfast.ai/api/mcp

Status

partial public mcp

Install gate

Inquiry-only until the deep-analysis loop contract, tenant install profile, CleverQ home-of-record routing, and external customer SLA are packaged.

Callable tools

stackfast.think.decide

Missing or gated tools

deep_analysis_loop_public_contract
cleverq_home_of_record_install_profile
external_customer_multi_pass_sla

The public product name is Governed Decision MCP; internal engine names are not customer-facing.
Use for decision support and artifact review, not autonomous action.

Install and activate

Connect this product through the StackFast MCP endpoint. Discovery metadata is public; execution uses OAuth and storefront entitlement checks.

MCP URL

https://stackfast.ai/api/mcp

Agent subscription

This product remains request-scope until its checkout, fulfillment, and public-name gates are complete.

Client snippets

ChatGPT

Add StackFast as a custom MCP connector, then approve OAuth when prompted.

Claude

Connect a remote MCP server using the StackFast MCP URL and a tenant-scoped token or OAuth flow.

Cursor

Grok

Add StackFast as a custom MCP connector using the StackFast MCP URL and customer entitlement auth.

Product: StackFast Governed Decision MCP
Product API: https://stackfast.ai/api/store/products/governed-decision-mcp
Pricing API: https://stackfast.ai/api/store/pricing/governed-decision-mcp
Manifest API: https://stackfast.ai/api/store/manifests/governed-decision-mcp
MCP URL: https://stackfast.ai/api/mcp
Auth: oauth_reader_or_storefront_entitlement
Checkout session API: https://stackfast.ai/api/store/checkout/session
Plans:
- Governed decision install: Request scope; checkout_ready=false; checkout_url=request_scope
Agent activation:
- Read this product manifest and pricing API.
- If a plan has checkout_ready=true, open its checkout_url or POST product_slug, plan_slug, and customer_email to the checkout session API.
- After Stripe payment, the signed webhook grants storefront_entitlements for the buyer email/account.
- Connect the LLM client to the MCP URL and approve OAuth so tools/list reflects the licensed reader surface.
- Call only tools exposed for that entitlement; unentitled execution must fail closed.

Agent-readable queries

governed decision MCPdeep think MCP for agentsAI decision support with evidence and gapstraceable decision analysis MCPStackFast think decide toolhidden factor discovery for business decisions