MCP App Store
by KeenEthics
Bastyn icon

Bastyn MCP Server for Claude

By RootedLogic

Overview

Bastyn answers two planning questions about an AI agent, from the details you give your assistant. 1. Which regulations and standards may apply. For each regulation it returns a status (applies, likely applies, can't tell, does not apply), whether the rule is specific to the agent's sector or broad, and the reason. It also lists matching standards, regions with no rules on file, and the questions whose answers would settle each "can't tell". 2. Which technology categories the agent needs. Each category is marked applicable, not needed or can't tell yet, with a reason. Applicable categories list candidate products from Bastyn's catalogue. These are catalogue entries, not recommendations or endorsements, and carry no security rating. Both tools are read-only and free. Nothing you ask is stored, and no AI model is called to produce the answer: the result is a rules-based indication from the facts you declared. A missing answer is reported as a gap, never as "does not apply". Not legal advice. The regulation mappings have not yet been reviewed by a lawyer. Check anything you rely on with a qualified professional. Sign-in: you sign in to your Bastyn account (email or GitHub) when the assistant first calls a tool. Listing the tools does not need sign-in. Please do not type confidential text into the free-text field.

How to connect

  1. Claude: Open the Bastyn listing in the Claude connectors directory and choose Connect. Claude listing Bastyn exposes 2 tools here.

Tools

check_regulations_and_standards

Claude
Looks up which regulations and standards may apply to an AI agent, from Bastyn's knowledge base, using the details the user has given about the agent. For each regulation it returns a status (applies, likely applies, can't tell, does not apply), whether the rule is specific to the agent's sector or broad, and the reason. It also returns matching standards, regions with no rules on file, and the questions whose answers would settle each 'can't tell'. All inputs are optional and a 'not sure' value is accepted; anything not provided is reported as a gap, never as 'does not apply'. A useful result needs some details about the agent: what it does, who uses it, what data it handles and which regions. Read-only; nothing is stored and no AI model is called. A rules-based indication from self-declared answers, not legal advice. It does not quote the text of a specific law and does not select technology.

recommend_tech_stack

Claude
Shows which of Bastyn's technology categories an AI agent needs, from the details the user has given about the agent. Each category is marked applicable, not needed or can't tell yet, with a reason; applicable categories list candidate products from Bastyn's catalogue. Candidates are catalogue entries, not recommendations or endorsements, and carry no security rating (no vulnerability data means 'no data', not 'low risk'). This is the rules-based part only. All inputs are optional and a 'not sure' value is accepted. A useful result needs some details about the agent: what it does, who uses it, what data it handles and which regions. Read-only; nothing is stored and no AI model is called. Not legal advice. It does not answer regulation or compliance questions.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/bastyn"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/bastyn)