Skip to content

Atlasemoji MCP server

com.atlasemoji/mcpatlasemoji.comstreamable-httpv0.1.0Scanned

AI-ready GIS, geofencing, DataSynch, CRM, inventory, routing, APIs, telemetry and workflows.

19 tools: 5 change things and 14 only read.

Tools: 0 delete, 0 irreversible, 5 write, 14 read.
  • Reads private data · 3
  • Reads text others write · 8
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

5 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 Atlasemoji MCP server can do

The Atlasemoji MCP server is published by atlasemoji.com, a domain the MCP Registry verified. It has 19 tools. It can create or change data (5 tools: verify_atlas_agent, detect_location_columns, check_point_in_geofence, suggest_field_mapping and 1 more), but cannot delete data. 14 tools only read.

3 tools read private data (get_atlas_profile, get_failed_runs and detect_file_schema); 8 tools bring in text other people can write (get_atlas_profile, verify_atlas_agent, get_datasynch_run_status and 5 more).

The fixed checks matched 2 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 12, 2026, version 0.1.0.

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.

19 tools

Changes things 5Claude Code: ask
  • check_point_in_geofenceEvaluate whether a vehicle, shipment, mobile device, scan, person-authorized location event, asset, aircraft, vessel, or other coordinate is inside a proposed radius boundary used …1 finding

    Why it is in this group

    • The description's first verb is "evaluate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "check_point_in_geofence" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Evaluate whether a vehicle, shipment, mobile device, scan, person-authorized location event, asset, aircraft, vessel, or other coordinate is inside a proposed radius boundary used in Atlasemoji geofencing and event-driven workflows.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • detect_location_columnsIdentify address, city, state, province, region, postal code, latitude, and longitude fields in supplied business or operational records so they can be connected to Atlasemoji loca…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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Identify address, city, state, province, region, postal code, latitude, and longitude fields in supplied business or operational records so they can be connected to Atlasemoji locations, customer sites, facilities, routes, territories, inventory, telemetry, geofences, and DataSynch workflows.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • suggest_field_mappingSuggest an initial bridge between external partner, API, ERP, WMS, TMS, CRM, file, EDI-normalized, EDIFACT-normalized, cXML-derived, inventory, telemetry, item, and location fields…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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Suggest an initial bridge between external partner, API, ERP, WMS, TMS, CRM, file, EDI-normalized, EDIFACT-normalized, cXML-derived, inventory, telemetry, item, and location fields and common Atlasemoji data targets. Intended to support integration design and human-reviewed mapping preparation.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • verify_atlas_agentComplete proof of life for an already configured Atlas Agent MCP connection.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Complete proof of life for an already configured Atlas Agent MCP connection. The authenticated MCP principal must be authorized for the requested company and for this tool. Atlas verifies that the connection belongs to the requested Agent and records the current Manifest revision before returning a sanitized Connection Card.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • wanderloop.research_placeAssemble a cited, geographically grounded Wanderloop research package for a location.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Assemble a cited, geographically grounded Wanderloop research package for a location. Queries Atlasemoji-approved historical, archival, academic, environmental, wildlife, and place-record providers through the same provider registry used by the Wanderloop application. Returns evidence records, provider execution status, citations, GeoJSON map features, and saved manifest links. This is evidence assembly, not an unsupported AI-written story.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 14Show 14 read-only tools
  • detect_file_schemaAnalyze a bounded preview of CSV, spreadsheet, JSON, EDI-normalized, EDIFACT-normalized, cXML-derived, inventory, telemetry, CRM, item, location, shipment, or partner records to id…Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "analyze": a word for reading.

    What it can reach

    • private-dataThe name "detect_file_schema" says "file": it reads files.
    Description, as the server wrote it
    Analyze a bounded preview of CSV, spreadsheet, JSON, EDI-normalized, EDIFACT-normalized, cXML-derived, inventory, telemetry, CRM, item, location, shipment, or partner records to identify their structure and determine how they may fit Atlas DataSynch workflows.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_atlas_profileReturn the Atlasemoji profile represented by the current authenticated MCP credentials so ChatGPT can identify the connected Atlas account.Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "get_atlas_profile" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "return" and "credential": it reads secrets.
    • untrusted-inputThe description's first sentence says "return" and "chat": it reads messages, which other people can write.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...sented by the current authenticated MCP credentials so ChatGPT can identify the connected A..."

      What this check looks for
    Description, as the server wrote it
    Return the Atlasemoji profile represented by the current authenticated MCP credentials so ChatGPT can identify the connected Atlas account. This operation is read-only and never accepts a user or account identifier from the model.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_datasynch_run_statusSupport Atlas DataSynch operations by retrieving recent processing and workflow status for an authorized company, workspace, or manifest.Reads text others writeNo findings

    Why it is in this group

    • The name "get_datasynch_run_status" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Support Atlas DataSynch operations by retrieving recent processing and workflow status for an authorized company, workspace, or manifest. Agents can use the result to explain integration progress, identify stalled activity, and understand the current state of EDI, EDIFACT, cXML, API, file, telemetry, inventory, location, and partner-data workflows.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_failed_runsHelp support, implementation, operations, and partner agents investigate failed Atlas DataSynch activity across APIs, files, EDI, EDIFACT, cXML, mappings, inventory, telemetry, loc…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_failed_runs" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Help support, implementation, operations, and partner agents investigate failed Atlas DataSynch activity across APIs, files, EDI, EDIFACT, cXML, mappings, inventory, telemetry, locations, and downstream workflows. Returns authorized failure and exception context without changing workflow records.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_manifest_summaryRetrieve authorized Atlasemoji manifest context so an agent can understand the places, routes, boundaries, layers, records, workflow purpose, workspace relationship, and operationa…Reads text others writeNo findings

    Why it is in this group

    • The name "get_manifest_summary" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Retrieve authorized Atlasemoji manifest context so an agent can understand the places, routes, boundaries, layers, records, workflow purpose, workspace relationship, and operational context represented by the manifest.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_capabilitiesDiscover how Atlasemoji supports Atlas DataSynch, GIS, geofencing, CRM, inventory, Atlas Intercept, handheld scanning, APIs, integrations, routing, storytelling, learning, and part…No findings

    Why it is in this group

    • The name "list_capabilities" says "list": a word for reading.
    Description, as the server wrote it
    Discover how Atlasemoji supports Atlas DataSynch, GIS, geofencing, CRM, inventory, Atlas Intercept, handheld scanning, APIs, integrations, routing, storytelling, learning, and partner workflows. Returns the related public APIs, partner access paths, production capabilities, current MCP tools, learning opportunities, and access requirements for each solution.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • preview_datasynch_rowsReview a bounded preview of partner, customer, ERP, WMS, TMS, CRM, inventory, telemetry, location, API, spreadsheet, EDI-normalized, EDIFACT-normalized, or cXML-derived records in …Reads text others writeNo findings

    Why it is in this group

    • The name "preview_datasynch_rows" says "preview": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Review a bounded preview of partner, customer, ERP, WMS, TMS, CRM, inventory, telemetry, location, API, spreadsheet, EDI-normalized, EDIFACT-normalized, or cXML-derived records in the context of an authorized Atlasemoji company, workspace, or manifest.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • preview_geofencePrepare a radius-based geofence for an Atlasemoji location-aware workflow.No findings

    Why it is in this group

    • The name "preview_geofence" says "preview": a word for reading.
    Description, as the server wrote it
    Prepare a radius-based geofence for an Atlasemoji location-aware workflow. Helps agents and users evaluate the proposed center, radius, coverage area, label, and tenant context before using production geofencing for movement, scans, arrivals, exits, dwell, proximity, telemetry, alerts, or downstream actions.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • summarize_workspace_activitySummarize recent authorized activity across an Atlasemoji company, workspace, or manifest so agents can explain what has happened across DataSynch, locations, manifests, integratio…Reads text others writeNo findings

    Why it is in this group

    • The name "summarize_workspace_activity" says "summarize": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Summarize recent authorized activity across an Atlasemoji company, workspace, or manifest so agents can explain what has happened across DataSynch, locations, manifests, integrations, telemetry, exceptions, inventory, partner workflows, and operational records.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • validate_coordinatesPrepare latitude and longitude values for Atlasemoji maps, routes, geofences, telemetry, mobile events, customer locations, assets, vessels, aircraft, storytelling, and operational…No findings

    Why it is in this group

    • The name "validate_coordinates" says "validate": a word for reading.
    Description, as the server wrote it
    Prepare latitude and longitude values for Atlasemoji maps, routes, geofences, telemetry, mobile events, customer locations, assets, vessels, aircraft, storytelling, and operational workflows by checking accepted geographic ranges and returning normalized coordinates.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • validate_geojsonPrepare GeoJSON features, collections, points, lines, polygons, and geometry collections for Atlasemoji maps, routes, service areas, stories, manifests, geofences, learning exercis…No findings

    Why it is in this group

    • The name "validate_geojson" says "validate": a word for reading.
    Description, as the server wrote it
    Prepare GeoJSON features, collections, points, lines, polygons, and geometry collections for Atlasemoji maps, routes, service areas, stories, manifests, geofences, learning exercises, APIs, and location-aware workflows by checking their basic structure.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • validate_manifest_schemaPrepare geographic and operational manifest data for Atlasemoji use.No findings

    Why it is in this group

    • The name "validate_manifest_schema" says "validate": a word for reading.
    Description, as the server wrote it
    Prepare geographic and operational manifest data for Atlasemoji use. Checks the supplied manifest structure, durable identity, locations, addresses, and coordinates before the data is used with workspaces, routes, storytelling, geofencing, DataSynch, inventory, CRM, or other Atlasemoji workflows.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • wanderloop.get_manifestRetrieve a previously saved Wanderloop topic or place-research manifest by manifest ID, including its normalized provider evidence, statuses, map data, citations, and source links …No findings

    Why it is in this group

    • The name "wanderloop.get_manifest" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve a previously saved Wanderloop topic or place-research manifest by manifest ID, including its normalized provider evidence, statuses, map data, citations, and source links when available.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • wanderloop.list_provider_capabilitiesList every registered Wanderloop source integration without dropping unavailable or unconfigured providers.No findings

    Why it is in this group

    • The name "wanderloop.list_provider_capabilities" says "list": a word for reading.
    Description, as the server wrote it
    List every registered Wanderloop source integration without dropping unavailable or unconfigured providers. Returns provider identity, current topic assignment, execution mode, and required environment configuration so an agent can understand which historical, academic, archival, environmental, and natural-history sources Atlasemoji can invoke.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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 outbound.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write8
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:34 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://atlasemoji.com/.well-known/oauth-protected-resource/api/mcp
Authorization servers
https://atlasemoji.com
Legacy HTTP+SSE transport
no
Dynamic client registration
no
Client ID metadata documents
yes
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://atlasemoji.com/api/mcp: tools/list returned 19 tools to an anonymous client, including verify_atlas_agent (write), detect_location_columns (write), check_point_in_geofence (write), suggest_field_mapping (write), wanderloop.research_place (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn1 info
  • The server marks "check_point_in_geofence" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "evaluate": a word for a change.

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...sented by the current authenticated MCP credentials so ChatGPT can identify the connected A..."

    What this check looks for

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http atlasemoji https://atlasemoji.com/api/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http atlasemoji https://atlasemoji.com/api/mcp --header 'Authorization: <your-authorization>'

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__atlasemoji__list_capabilities",
      "mcp__atlasemoji__get_atlas_profile",
      "mcp__atlasemoji__get_datasynch_run_status",
      "mcp__atlasemoji__get_failed_runs",
      "mcp__atlasemoji__validate_manifest_schema",
      "mcp__atlasemoji__get_manifest_summary",
      "mcp__atlasemoji__validate_coordinates",
      "mcp__atlasemoji__validate_geojson",
      "mcp__atlasemoji__preview_geofence",
      "mcp__atlasemoji__detect_file_schema",
      "mcp__atlasemoji__preview_datasynch_rows",
      "mcp__atlasemoji__summarize_workspace_activity",
      "mcp__atlasemoji__wanderloop_get_manifest",
      "mcp__atlasemoji__wanderloop_list_provider_capabilities"
    ],
    "ask": [
      "mcp__atlasemoji__verify_atlas_agent",
      "mcp__atlasemoji__detect_location_columns",
      "mcp__atlasemoji__check_point_in_geofence",
      "mcp__atlasemoji__suggest_field_mapping",
      "mcp__atlasemoji__wanderloop_research_place"
    ],
    "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 atlasemoji. Review it before you use it.

Capability tags behind 9 rules
  • mcp__atlasemoji__get_atlas_profile private-data, untrusted-input
  • mcp__atlasemoji__verify_atlas_agent untrusted-input
  • mcp__atlasemoji__get_datasynch_run_status untrusted-input
  • mcp__atlasemoji__get_failed_runs private-data, untrusted-input
  • mcp__atlasemoji__get_manifest_summary untrusted-input
  • mcp__atlasemoji__detect_file_schema private-data
  • mcp__atlasemoji__preview_datasynch_rows untrusted-input
  • mcp__atlasemoji__summarize_workspace_activity untrusted-input
  • mcp__atlasemoji__wanderloop_research_place untrusted-input

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.atlasemoji/mcp/verify?hash=2f54e13dd69f81d5f03461388a68f05d7edd7d3a8cd1b0289ce275118a3c7232" | jq -e '.changed == false'

Pinned hash 2f54e13dd69f, 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.atlasemoji/mcp/changes.xml

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

Badge

Anlyon Radar badge for com.atlasemoji/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/com.atlasemoji/mcp.svg)](https://radar.anlyon.com/servers/com.atlasemoji/mcp)

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

Atlasemoji MCP server: questions and answers

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

Is the Atlasemoji MCP server safe?

No scan can promise that. What its definitions show: 19 tools, 5 of which can change, send or delete something, and 2 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 Atlasemoji MCP server delete data?

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

Can the Atlasemoji 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 Atlasemoji MCP server have?

19 tools: 5 write, 14 read. verify_atlas_agent, detect_location_columns, check_point_in_geofence, suggest_field_mapping, wanderloop.research_place, list_capabilities, get_atlas_profile, get_datasynch_run_status and 11 more.

Does the Atlasemoji MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Atlasemoji MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Atlasemoji MCP server changed its tools?

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