Deep Noodle AI Atlas is answering right now. Last checked 11 min ago. It exposes 10 tools.
Read-only, sourced AI history, organizations, stories, and model facts.
Uptime history
46 days of history · worst day 92%
46 days agonow
100.0%
Uptime 24h
91 of 91 checks
10
Tools
read from the server
161 ms
Response time
average over 24h
open, no key
Access
streamable-http
What changed 12
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 23 September 2026. No other catalogue keeps this.
20 Oct
2 tools changed the parameters they ask for
get_model, list_models
1 Oct
3 tools changed the parameters they ask for6 times that day
compare_models, get_model, list_models
24 Sep
a tool description was rewritten
search_atlas
24 Sep
a tool changed version
23 Sep
2 tools changed the parameters they ask for
list_models, search_atlas
and 3 more, back to 23 September 2026
Nothing serious here today
Today is the operative word: we check Deep Noodle AI Atlas every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.
run in your terminal
claude mcp add atlas --transport http https://deepnoodle.ai/atlas/mcpSettings → Connectors → Add custom connector, then paste this address
https://deepnoodle.ai/atlas/mcp~/.codex/config.toml
[mcp_servers.atlas]
url = "https://deepnoodle.ai/atlas/mcp".cursor/mcp.json
{
"mcpServers": {
"atlas": {
"url": "https://deepnoodle.ai/atlas/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"atlas": {
"type": "http",
"url": "https://deepnoodle.ai/atlas/mcp"
}
}
}Available tools 10
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
atlas
search_atlas
Find relevance-ranked events, briefs, organizations and models. entities lists models and organizations whose full name appears in q, best first; read those before events. Default match=any; use match=all for every term; sort=most-linked ranks distinct published inbound neighbors before pagination. Event filters constrain events and organization facets; organization matches and briefs are separately labeled. Each result family has pagination metadata. Organization name/evidence matches are returned only with q; organizationFacets always describes filtered events. For what happened recently, use since/until here; for records published or edited recently, use get_changes.
changes
get_changes
Current-record feed of additions and revisions since a date. Uses publication timestamps, not occurrence dates. For what happened recently, use search_atlas with since/until instead. Publication backfills can include many older events here. This is not a historical diff or deletion log.
compare
compare_models
Compare two to four catalog IDs or unambiguous API identifiers in requested order. Defaults include compact release, lifecycle, specs and token prices, sourceRefs and a website link. fields selects facts such as pricing. Unknown values stay explicit. IDs must resolve to distinct records.
event
get_event
Read compact event facts, sources, date precision, revisions, contextual links and story connections. Request include=["explanation"] for the full narrative. hasExplanation and explanationScope describe availability. explanationCoverage counts published event explanations across the corpus; empty links can mean unwritten context, not an unconnected event.
events
get_events
Read 1–20 published event details in request order. Unknown or unpublished IDs are returned in missingIds. Explanations remain opt-in; each event has independently paginated incoming and outgoing context.
model
get_model
Read a model by exact catalog ID or unambiguous API identifier. Defaults to core facts; fields selects fact groups such as pricing. sourceRefs resolve through atlas://models/sources. Ambiguous or missing lookups return candidate IDs; surface disambiguates hosts.
models
list_models
Browse compact model facts with search, filters, sorting and nextOffset pagination. Read atlas://models/catalog for filter values and price units. Defaults to current models, newest documented release first. matchedUnknown reports unverified capability alternatives only when capability filters are used; includeUnknown=true includes them. undatedMatches reports relevant undated records; releaseDateKnown=false browses them. Unknown is not unsupported, free or older.
organization
get_organization
Read compact sourced organization facts and paginated events. Request include=["explanation"] for the full narrative; hasExplanation and explanationScope describe availability. Subsidiaries and successors are separate.
stories
list_stories
Enumerate published briefs with review dates, evidence cutoffs, and pagination.
story
get_story
Read narrative, labeled interpretation, citations, chronology, open questions and Markdown. Newer research leads use strict phrase matches and are separate from reviewed narrative.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://deepnoodle.ai/atlas/mcp | streamable-http | answering | 139 ms | 11 min ago |
Alternatives to Deep Noodle AI Atlas
same job, measured the same wayvoar
by voar
Read your organization's GitHub Actions jobs and usage on voar. Read-only.
Hong Kong Insurance Connect
by buyhongkonginsurance
Read-only sourced Hong Kong insurance facts and referral links. No product recommendations.
COLA Insight
by ge3m0r
Read-only Social Security COLA data, calculations, history, and official source links.
AI Pensieve MCP
by as-xs
Search and cross-reference local AI chat history with read-only tools and source citations.
Civica citizenship test prep
by citizenleap
Read-only citizenship test facts, official sources and sample questions for 8 countries.
J
JP Election Discovery
by pages-jp-election-mcp
Read-only index to Japanese election data, official sources, relations and scoped search history.
ET Ducky
by etducky
Read-only access to an ET Ducky organization's agents, alerts, and fleet summary
Seiche Market Atlas Corpus
by beepboop2025
Read-only corpus catalogs and bounded observations with source dates and rights metadata.
Deep Noodle AI Atlas — questions
Answers built from our own checks of this server.
What can Deep Noodle AI Atlas do?
It exposes 10 tools, read directly from the server on our last check. Among them: compare_models, get_changes, get_event, get_events, get_model, get_organization and 4 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is Deep Noodle AI Atlas working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 161 ms. The bar chart above shows every period we have measured.
How do I connect Deep Noodle AI Atlas?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Deep Noodle AI Atlas need an API key?
No. Deep Noodle AI Atlas completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 10 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Deep Noodle AI Atlas?
It answers our handshake in 161 ms on average, which is faster than 82% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.