Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

dev.agentic-atlas/atlas

REMOTE · AGENTIC-ATLAS.DEV · SCANNED SEP 22

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

+3 this week 83 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
Transport & Reachability100
Schema Quality & AI Usability82
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1813 tokens (~164/item across 11 items; 5 tools + 6 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management59
  • Stability check failed: schema churn in the 29 days we've observed: 3 tool removals, 0 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
  • Supports UI / widget rendering.Pass
Install

How do I install the dev.agentic-atlas/atlas MCP server?

dev.agentic-atlas/atlas is a hosted endpoint at https://agentic-atlas.dev/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · agentic-atlas.dev

# add to Claude Code
claude mcp add --transport http dev-agentic-atlas-atlas 'https://agentic-atlas.dev/mcp/'
// .cursor/mcp.json
{
  "mcpServers": {
    "dev-agentic-atlas-atlas": {
      "url": "https://agentic-atlas.dev/mcp/"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "dev-agentic-atlas-atlas": {
      "type": "http",
      "url": "https://agentic-atlas.dev/mcp/"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.dev-agentic-atlas-atlas]
url = "https://agentic-atlas.dev/mcp/"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-agentic-atlas-atlas": {
      "type": "remote",
      "url": "https://agentic-atlas.dev/mcp/",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add dev-agentic-atlas-atlas --url 'https://agentic-atlas.dev/mcp/' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  dev-agentic-atlas-atlas:
    url: "https://agentic-atlas.dev/mcp/"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "dev-agentic-atlas-atlas": {
      "Transport": "http",
      "Url": "https://agentic-atlas.dev/mcp/"
    }
  }
}
# add to Vellum
assistant mcp add dev-agentic-atlas-atlas -t streamable-http -u 'https://agentic-atlas.dev/mcp/'
// mcp.json
{
  "mcpServers": {
    "dev-agentic-atlas-atlas": {
      "type": "http",
      "url": "https://agentic-atlas.dev/mcp/"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 56.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 46 to 49.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 39 to 43.

  • 15 Sept 26 +1
    • Server version: 1.0.6 → 1.0.9 functional
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 26 to 29.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 19 to 22.

  • 9 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 16. Other categories moved too: Schema Quality & AI Usability rose 1.

  • 8 Sept 26 −6
    • Stability: 0.47 → fail security
    • Tool “atlas_decisions” was removed security
    • Tool “atlas_define” was removed security
    • Tool “atlas_provenance” was removed security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “atlas_cards” rewrote its description, which is the text the model reads security
    • Tool “atlas_orient” rewrote its description, which is the text the model reads security
    • Tool “atlas_read” rewrote its description, which is the text the model reads security
    • Schema quality: 138 → 164 functional
    • Server version: 1.0.5 → 1.0.6 functional
    • “atlas_cards” added an optional parameter “provenance” cosmetic
    • “atlas_orient” reworded the description of “kind” cosmetic
    • “atlas_orient” reworded the description of “query” cosmetic
    • “atlas_read” reworded the description of “address” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 22 Sept 2026 · Probed https://agentic-atlas.dev/mcp/

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=agentic-atlas.dev CN=YR1,O=Let's Encrypt,C=US 25 Jul 2026 23 Oct 2026 RSA 2048 SHA256-RSA 6d9d36afd58d88705c1e4062e7022f9a7fe
SANs: agentic-atlas.dev
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of agentic-atlas.dev. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
dev. present 60074 8 Verified
agentic-atlas.dev. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000
content-security-policy frame-ancestors 'none'
x-content-type-options nosniff
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agentic-atlas.dev/mcp/ Verified 200
http (plaintext) http://agentic-atlas.dev/mcp/ HTTPS enforced 308 https://agentic-atlas.dev/mcp/
MCP tools · 5 exposed · ~888 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
atlas_cards ~116

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. Use atlas_read for Section wording or a complete Node.

NameTypeReqDescription
expected_revisionA prior payload's 'coherence'; 'revision_changed' refuses a moved Release.
idsarrayyes1-4 distinct canonical node ids.
provenancebooleanInclude expanded audit facts for cited sources.
NameTypeReqDescription
coherencestringyes
dataobjectyes
payload_classstringyes
projectionyes
scopeobjectyes

No examples provided.

atlas_links ~133

Page one subject's relationship occurrences, outbound then inbound, each with direction, reference class, source Section, and the far end's Hook, plus its identity unless the class is 'undisclosed'. Use atlas_read for the full Node.

NameTypeReqDescription
boundintegerOccurrences per page, 1-50.
cursorscope.next_cursor from a prior atlas_links page; repeat the same other arguments.
expected_revisionA prior payload's 'coherence'; 'revision_changed' refuses a moved Release.
subjectstringyesThe node id whose occurrences are paged.
NameTypeReqDescription
coherencestringyes
dataobjectyes
payload_classstringyes
projectionyes
scopeobjectyes

No examples provided.

atlas_navigate ~89

Read 'tree', the canonical ordered traversal of every published node, or 'tour', the publisher-curated first learning path. Use atlas_orient for relevance-ranked discovery.

NameTypeReqDescription
expected_revisionA prior payload's 'coherence'; 'revision_changed' refuses a moved Release.
viewstring'tree' for the canonical traversal, 'tour' for the curated walk.
NameTypeReqDescription
coherencestringyes
dataobjectyes
payload_classstringyes
projectionyes
scopeobjectyes

No examples provided.

atlas_orient ~387

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.

NameTypeReqDescription
boundintegerCandidates per page, 1-8.
cursorscope.next_cursor from a prior atlas_orient page; repeat the same other arguments.
expected_revisionA prior payload's 'coherence'; 'revision_changed' refuses a moved Release.
kindRestrict to 'pattern', 'concept', 'example', or 'decision', or 'term'; any kind excludes Roadmap entries. Decision and term candidates carry directly readable addresses.
querystringyesOrdinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks…
statusOne status-ladder rung; published subjects are 'fleshed' or 'stable'.
NameTypeReqDescription
coherencestringyes
dataobjectyes
payload_classstringyes
projectionyes
scopeobjectyes

No examples provided.

atlas_read ~163

Read a complete Node (bare id: identity, hierarchy, Hook, and every Section — relationships are recovered through atlas_links), one Section ('node-id#section-slug'), one Decision record ('decision:<decision-id>'), or one exact glossary definition ('term:<key>'). A Card from atlas_cards is usually cheaper than a whole Node.

NameTypeReqDescription
addressstringyesA bare node id; 'node-id#section-slug', the slug read off a Node's sections, a Card claim's sources, or a Link's occurrence (slugs are not guessable); or 'decision:<decision-id>'; or 'term:<key>'.
expected_revisionA prior payload's 'coherence'; 'revision_changed' refuses a moved Release.
NameTypeReqDescription
coherencestringyes
dataobjectyes
payload_classstringyes
projectionyes
scopeobjectyes

No examples provided.

Common questions

What is the dev.agentic-atlas/atlas MCP server?

dev.agentic-atlas/atlas is an MCP server listed in the public MCP registry as dev.agentic-atlas/atlas. Agent-design pattern guidance via 5 hosted read-only tools; Streamable HTTP, no auth, one Release. This page covers its hosted endpoint (https://agentic-atlas.dev/mcp/).

Is the dev.agentic-atlas/atlas MCP server safe to use?

dev.agentic-atlas/atlas scores 83 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the dev.agentic-atlas/atlas MCP server expose?

dev.agentic-atlas/atlas exposes 5 tools: atlas_orient, atlas_cards, atlas_read, atlas_links, atlas_navigate. Their descriptions and schemas cost roughly 888 tokens of context every time the server is loaded.

Does the dev.agentic-atlas/atlas MCP server require authentication?

No. We connected to dev.agentic-atlas/atlas without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the dev.agentic-atlas/atlas MCP server still maintained?

dev.agentic-atlas/atlas is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.