Skip to content

Atlas Data Exchange MCP server

com.atlasipholdingsllc.app/atlas-data-exchangeapp.atlasipholdingsllc.comstreamable-httpv2026.9.11-2Scanned

Infrastructure and hazard intelligence with provenance, spatial confidence and quality contracts.

10 tools: 6 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 6 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • No findings

Sign-in required, no OAuth metadata. Remote posture

With Anlyon

6 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Atlas Data Exchange MCP server can do

The Atlas Data Exchange MCP server is published by app.atlasipholdingsllc.com, a domain the MCP Registry verified. It has 10 tools. It can create or change data (6 tools: sample_product, answer_question, quote_request, quote_watch and 2 more), but cannot delete data. 4 tools only read.

1 tool brings in text other people can write (search_products); 1 tool can send data out of your system (create_watch).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Last scanned Nov 12, 2026, version 2026.9.11-2.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

10 tools

Changes things 6Claude Code: ask
  • answer_questionAsk a question Atlas can answer live (seismic unusual in a region, wave energy, commodity regimes, logistics safety, what cells are alert-worthy).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Ask a question Atlas can answer live (seismic unusual in a region, wave energy, commodity regimes, logistics safety, what cells are alert-worthy). Returns verdict, evidence, datasets and the purchase path.
  • buy_productThe exact purchase call for a product and tier (one-time pack via POST /api/datapacks/buy, subscription via POST /api/feeds/subscribe), with terms, idempotency and what is metered.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    The exact purchase call for a product and tier (one-time pack via POST /api/datapacks/buy, subscription via POST /api/feeds/subscribe), with terms, idempotency and what is metered. Does not move money: purchases need a session (or Stripe checkout).
  • create_watchThe exact subscribe call for a watch (mode=watch) with the filters given, its tier, price and metering, plus the webhook contract.Can send data outNo findings

    Why it is in this group

    • The name "create_watch" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    The exact subscribe call for a watch (mode=watch) with the filters given, its tier, price and metering, plus the webhook contract. Does not move money.
  • quote_requestQuote a dataset need: text / keywords / category, max_age_hours, budget_usd, resolution, window_days, records, region or bbox.No findings

    Why it is in this group

    • The name "quote_request" says "request": a word for a change.
    Description, as the server wrote it
    Quote a dataset need: text / keywords / category, max_age_hours, budget_usd, resolution, window_days, records, region or bbox. Returns ranked products with the cheapest fitting tier, estimated records and credits, cost, and the exact purchase call.
  • quote_watchQuote a watch (signal feed): need text plus filters (bbox, cohorts, signals, min_severity, min_confidence) -> product (ranked like quote_request, among packs with the cell layer), …No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Quote a watch (signal feed): need text plus filters (bbox, cohorts, signals, min_severity, min_confidence) -> product (ranked like quote_request, among packs with the cell layer), cheapest tier that meets the need, best tier within budget, estimated events per month and credits (watch events cost 5 credits).
  • sample_productFree sample rows of a product (k-anonymised where applicable) with data_through and contract version.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Free sample rows of a product (k-anonymised where applicable) with data_through and contract version.
Only reads 4Show 4 read-only tools
  • get_changesChange events since a cursor.No findings

    Why it is in this group

    • The name "get_changes" says "get": a word for reading.
    Description, as the server wrote it
    Change events since a cursor. Anonymous: the latest-day preview, at most 10 events (limit_applied/limit_max in the response). With api_key: the metered signal feed for that subscription (GET /api/feeds/{slug}/changes).
  • get_entitlementWhat an api_key is entitled to and has used: tier, credits quota, used, remaining, projected cost of a request, reset date.No findings

    Why it is in this group

    • The name "get_entitlement" says "get": a word for reading.
    Description, as the server wrote it
    What an api_key is entitled to and has used: tier, credits quota, used, remaining, projected cost of a request, reset date.
  • inspect_productThe full machine-readable commercial contract of one product: pricing ladder, credit multipliers, views, schema, measured quality, SLOs, provenance, join quality, semantics (ships …No findings

    Why it is in this group

    • The name "inspect_product" says "inspect": a word for reading.
    Description, as the server wrote it
    The full machine-readable commercial contract of one product: pricing ladder, credit multipliers, views, schema, measured quality, SLOs, provenance, join quality, semantics (ships through risk indicator), limitations.
  • search_productsSEMANTIC product discovery: describe the need in plain words (industry, infrastructure type, hazard, question) and get products ranked by profile match (answers_questions, use_case…Reads text others writeNo findings

    Why it is in this group

    • The name "search_products" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    SEMANTIC product discovery: describe the need in plain words (industry, infrastructure type, hazard, question) and get products ranked by profile match (answers_questions, use_cases, industries, infrastructure_types, hazard_classes, example_questions), with the matched terms, what each product is NOT for, its temporal/spatial coverage, the cheapest satisfying tier, quality status and contract URL.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 18:34 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
502
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

The probe stopped: initialize answered HTTP 502.

Posture changes

  1. Nov 20, 2026
    • HTTP status of an anonymous initialize: 200 to 502
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 6 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 502; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 6 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 502
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 6 to 0
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 2026.9.11-2. Values in angle brackets are yours to fill in.

claude mcp add --transport http atlas-data-exchange https://app.atlasipholdingsllc.com/mcp?src=mcp_registry
claude mcp add --transport http atlas-data-exchange https://app.atlasipholdingsllc.com/mcp?src=mcp_registry

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__atlas-data-exchange__search_products",
      "mcp__atlas-data-exchange__inspect_product",
      "mcp__atlas-data-exchange__get_changes",
      "mcp__atlas-data-exchange__get_entitlement"
    ],
    "ask": [
      "mcp__atlas-data-exchange__sample_product",
      "mcp__atlas-data-exchange__answer_question",
      "mcp__atlas-data-exchange__quote_request",
      "mcp__atlas-data-exchange__quote_watch",
      "mcp__atlas-data-exchange__buy_product",
      "mcp__atlas-data-exchange__create_watch"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as atlas-data-exchange. Review it before you use it.

Capability tags behind 2 rules
  • mcp__atlas-data-exchange__search_products untrusted-input
  • mcp__atlas-data-exchange__create_watch outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.atlasipholdingsllc.app/atlas-data-exchange/verify?hash=d2bdc0726b996f564bc9ee9132e4abc8c3f80504dbbbf52555b5c44f07d71924" | jq -e '.changed == false'

Pinned hash d2bdc0726b99, from Nov 12, 2026, 16:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.atlasipholdingsllc.app/atlas-data-exchange/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.atlasipholdingsllc.app/atlas-data-exchange
[![Anlyon Radar](https://radar.anlyon.com/badge/com.atlasipholdingsllc.app/atlas-data-exchange.svg)](https://radar.anlyon.com/servers/com.atlasipholdingsllc.app/atlas-data-exchange)

Source: MCP Registry. Synced Oct 21, 2026, 17:51 UTC.

Atlas Data Exchange MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Atlas Data Exchange MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 6 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Atlas Data Exchange MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Atlas Data Exchange MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Atlas Data Exchange MCP server have?

10 tools: 6 write, 4 read. sample_product, answer_question, quote_request, quote_watch, buy_product, create_watch, search_products, inspect_product and 2 more.

Does the Atlas Data Exchange MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Atlas Data Exchange MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_watch.

Has the Atlas Data Exchange MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.