# dev.agentic-atlas/atlas

> Agent-design pattern guidance via 5 hosted read-only tools; Streamable HTTP, no auth, one Release.

- name: dev.agentic-atlas/atlas
- version: 1.0.6
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/dev.agentic-atlas%2Fatlas
- tools: https://api.protogrid.dev/v1/servers/dev.agentic-atlas%2Fatlas/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "atlas": {
      "type": "http",
      "url": "https://agentic-atlas.dev/mcp/"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% ~updated-43d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 5 of 5 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,989 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 27 tool changes in 30 days
- fail `stability.rug_pull`: 6 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 1,989 tokens to load them all
- tool set hash: 322a83bcf4fedf886a37ca440dc91052
- tools last changed: 2026-10-20T03:49:37.330Z
- badge: [![protogrid quality](https://protogrid.dev/badge/dev.agentic-atlas/atlas.svg)](https://protogrid.dev/servers/dev.agentic-atlas/atlas)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-20 `atlas_navigate` changed (outputSchema)
- 2026-10-20 `atlas_links` changed (outputSchema)
- 2026-10-20 `atlas_read` changed (outputSchema)
- 2026-10-20 `atlas_cards` changed (outputSchema)
- 2026-10-20 `atlas_orient` changed (description, inputSchema, outputSchema)
  - before: 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. Ids, titles, Hooks (one-line summaries), and claims decide candidacy, Section text only when no subject matches those; order is identity score, then Section score, then how many words matched, then the publisher's order. Returns ranked ids with Hooks (a term's is its whole definition), paged with a cursor. A miss is an empty page; invalid arguments are refused as invalid_argument.
  - after: 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.
- 2026-10-19 `atlas_navigate` changed (outputSchema)
- 2026-10-19 `atlas_links` changed (outputSchema)
- 2026-10-19 `atlas_read` changed (outputSchema)
- 2026-10-19 `atlas_cards` changed (outputSchema)
- 2026-10-19 `atlas_orient` changed (inputSchema, outputSchema)

Full history: https://api.protogrid.dev/v1/servers/dev.agentic-atlas%2Fatlas/changes

## Remotes

- https://agentic-atlas.dev/mcp/ (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (5)

- `atlas_cards`: 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_links`: List where one Atlas Node references other entries (outbound) and where they reference it (inbound), outbound first. Use to find related entries or what points at this one. Each occurrence gives direction, class, source Section, and the far end's Hook (one-line summary), plus its id and title unless the class is 'undisclosed' (unpublished and unannounced). Results are paged: follow the cursor to the end before concluding nothing points here. An unknown or Roadmap-only (unpublished) subject is refused as invalid_argument.
- `atlas_navigate`: 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`: 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`: 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.