MCP App Store
by KeenEthics
Agentic Atlas icon

Agentic Atlas MCP Server for Claude and ChatGPT

By Avery Jones

Overview

Agentic Atlas helps you design and review agent systems: skills, subagents, plugins, hooks, and multi-agent workflows. Connect it, then ask Claude a design question in plain language. Claude looks up the patterns that fit your situation and answers from their published rulings, which you can check on agentic-atlas.dev. Reach for it while a design decision is still open: splitting a system into skills, subagents, or tools; deciding what a subagent carries in and hands back; keeping context lean in a long-running workflow; placing a verification step so a wrong answer gets caught; or reviewing a skill or plugin you have already written. Each pattern states a ruling, a worked example, and its links to related patterns. Every ruling links to the decision record that settled it, and every entry carries a maturity label, so you can tell field-tested advice from advice still earning its evidence. A glossary defines the working vocabulary, and a curated eight-step tour is the place to start. The connector is public and read-only. There is no sign-in, account, or payment, and it never writes anything. Setup and the full tool reference: https://agentic-atlas.dev/connect

How to connect

  1. Claude: Open the Agentic Atlas listing in the Claude connectors directory and choose Connect. Claude listing Agentic Atlas exposes 5 tools here.
  2. ChatGPT: Open the Agentic Atlas listing in the ChatGPT app directory and choose Connect. ChatGPT listing Agentic Atlas exposes 5 tools here.

Tools

atlas_cards

ChatGPT
Get one summary Card per Atlas Node id: its Hook (one-line summary) and the publisher's claims (thesis, law, when-to-reach, or claim), each citing its source Sections. Use when you hold ids and want their guidance without full text, such as to compare entries. Cards return in request order. Atomic: one unknown or Roadmap-only (unpublished) id refuses the whole batch as batch_not_atomic, naming the rejected ids.

atlas_navigate

ChatGPT
Browse the whole Atlas in the publisher's order: the canonical tree of every published Node, or the guided first learning path, an introduction then steps each naming a Node id with narration. Use to survey what exists or to start learning with no topic in mind. Neither view carries entry text or claims; the tour is null if none is published.

atlas_orient

ChatGPT
Find Atlas entries by topic when you hold no id; an id you already hold can be read directly. Searches Nodes (patterns, concepts, examples) and Roadmap entries (announced, unpublished); kind narrows it to one Node kind, Decisions, or glossary terms. Node discovery preserves leading lexical matches and adds related entries with task vocabulary, using references in either direction. Related candidates explain their connection; direct matches have no via. Empty listings and exact id/title lookups stay lexical. Returns ranked ids with Hooks (one-line summaries; a term's is its whole definition), paged with a cursor. A miss is an empty page; invalid arguments are refused as invalid_argument.

atlas_read

ChatGPT
Read the full text at one exact Atlas address. A bare Node id returns the whole entry: identity, tree position, Hook (one-line summary), and every Section; relationship occurrences are omitted. A Section, Decision, or glossary term address returns that one item. Use when a summary is not enough or you need exact wording to cite. An unknown or malformed address is refused as invalid_argument; a wrong slug's refusal lists the real ones.

atlas_cards

Claude
Read 1-4 canonical ids as one ordered Card per id: identity, Hook, and sealed claims with source addresses. Set provenance=true to expand every cited source's Release-bound audit facts in the same atomic response.

atlas_navigate

Claude
Read 'tree', the canonical ordered traversal of every published node, or 'tour', the publisher-curated first learning path.

atlas_orient

Claude
Discover canonical identity from an ordinary-language query — the entry point when no canonical id is held. Ranked: identity fields and sealed claims decide candidacy, Section text only when no identity field matches; ordered by identity score, then Section score, then how many words matched, then manifest position. Node candidates carry id, status, Hook, and disclosure class; Decision and term candidates carry exactly a read address and Hook. A term's Hook is its full sealed definition. Results are paged. A miss is a successful empty payload.

atlas_read

Claude
Read a complete Node (bare id: identity, hierarchy, Hook, and every Section; relationship occurrences are omitted), one Section ('node-id#section-slug'), one Decision record ('decision:<decision-id>'), or one exact glossary definition ('term:<key>').

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/agentic-atlas"><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/agentic-atlas)