DeepMap AI -- Earth Grounding MCP server
com.deepmapai/earth-groundingdeepmapai.comstreamable-httpv0.3.0Scanned
Verifiable Earth ground truth for AI agents: water, hazard, ground stability, resource, with proof.
11 tools: 10 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 7
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
10 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.
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 DeepMap AI -- Earth Grounding MCP server can do
The DeepMap AI -- Earth Grounding MCP server is published by deepmapai.com, a domain the MCP Registry verified. It has 11 tools. It can create or change data (10 tools: water_availability, seismic_hazard, ground_stability, resource_indication and 6 more), but cannot delete data. 1 tool only reads.
7 tools bring in text other people can write (water_availability, seismic_hazard, ground_stability and 4 more).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 13, 2026, version 0.3.0.
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.
11 tools
Changes things 10Claude Code: ask
capabilitiesWhat DeepMap AI can answer now + coverage counts (public aggregate; tracks the library, leaks no proprietary data).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 What DeepMap AI can answer now + coverage counts (public aggregate; tracks the library, leaks no proprietary data).
Annotations the server declares
- title: Capabilities
- openWorldHint: false
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
check_hypothesisHas this Earth-science hypothesis been tested?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 Has this Earth-science hypothesis been tested? Query the Null Museum + the Bitcoin-anchored hypothesis registry. A direct match returns the verdict + the positive control that proves the test was sensitive + the honest bound + the anchor -- so an agent never re-runs a dead idea.
Annotations the server declares
- title: Check Hypothesis (Null Museum)
- openWorldHint: false
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
ground_stabilitySubsidence / void / karst / fault risk from verified observations.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Subsidence / void / karst / fault risk from verified observations.
Annotations the server declares
- title: Ground Stability
- openWorldHint: true
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
ground_truthThe bundled five-question answer (water / stability / hazard / resource / provability) + one provenance record.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 The bundled five-question answer (water / stability / hazard / resource / provability) + one provenance record.
Annotations the server declares
- title: Ground Truth
- openWorldHint: true
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
resource_indicationGeothermal / mineral / water indication (gated, honest null).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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Geothermal / mineral / water indication (gated, honest null).
Annotations the server declares
- title: Resource Indication
- openWorldHint: true
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
run_controlled_testThe Lab-as-an-API: run a REAL, bounded controlled test at a location and get an honest verdict.Reads text others write1 finding
Why it is in this group
- The name "run_controlled_test" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "run_controlled_test" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "run_controlled_test" says "run": a word for a change.
Description, as the server wrote it The Lab-as-an-API: run a REAL, bounded controlled test at a location and get an honest verdict. DeepMap AI fetches real data, runs a lock-in detection with a local-background null AND a positive control (a known reference line must be recovered, else UNTESTABLE) -- so an agent gets a grounded result it cannot fake. Free tier runs a synthetic demo; the live lab is the authenticated tier. v1 recipe: periodic-signal detection on the geomagnetic field.
Annotations the server declares
- title: Run Controlled Test (Lab-as-an-API)
- openWorldHint: true
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
seismic_hazardSeismic hazard via the public, outcome-excluded prediction ledger (no platform-wide accuracy figure).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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Seismic hazard via the public, outcome-excluded prediction ledger (no platform-wide accuracy figure).
Annotations the server declares
- title: Seismic Hazard
- openWorldHint: true
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
space_weather_grid_riskGIC / space-weather exposure for infrastructure at a point.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 GIC / space-weather exposure for infrastructure at a point.
Annotations the server declares
- title: Space-Weather Grid Risk
- openWorldHint: true
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
verifyVerify a claim / the ledger hash chain against the Bitcoin-anchored record.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 Verify a claim / the ledger hash chain against the Bitcoin-anchored record.
Annotations the server declares
- title: Verify Provenance
- openWorldHint: false
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
water_availabilityWater availability at a point.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Water availability at a point. Free tier = public GRACE groundwater trend.
Annotations the server declares
- title: Water Availability
- openWorldHint: true
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
Only reads 1Show 1 read-only tool
list_nullsList DeepMap AI's documented nulls / bounds / retractions (the Null Museum), optionally by domain -- each with the positive control that makes it trustworthy.No findings
Why it is in this group
- The name "list_nulls" says "list": a word for reading.
Description, as the server wrote it List DeepMap AI's documented nulls / bounds / retractions (the Null Museum), optionally by domain -- each with the positive control that makes it trustworthy. We carry our own retractions; that is the credibility.
Annotations the server declares
- title: List Nulls (Null Museum)
- openWorldHint: false
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
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 or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- 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.
Looked at Nov 20, 2026, 18:37 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
- 10
- Protocol version
- 2026-07-28
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (10 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://deepmapai.com/mcp: tools/list returned 11 tools to an anonymous client, including water_availability (write), seismic_hazard (write), ground_stability (write), resource_indication (write), space_weather_grid_risk (write) and 5 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "run_controlled_test" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "run_controlled_test" says "run": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:capabilitiesChanges thingsdescription
- Changed:list_nullsOnly readsdescription
- Changed:run_controlled_testChanges thingsdescription
Install
Pinned to version 0.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http earth-grounding https://deepmapai.com/mcpclaude mcp add --transport http earth-grounding https://deepmapai.com/mcpRun 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.
{
"permissions": {
"allow": [
"mcp__earth-grounding__list_nulls"
],
"ask": [
"mcp__earth-grounding__water_availability",
"mcp__earth-grounding__seismic_hazard",
"mcp__earth-grounding__ground_stability",
"mcp__earth-grounding__resource_indication",
"mcp__earth-grounding__space_weather_grid_risk",
"mcp__earth-grounding__verify",
"mcp__earth-grounding__ground_truth",
"mcp__earth-grounding__capabilities",
"mcp__earth-grounding__check_hypothesis",
"mcp__earth-grounding__run_controlled_test"
],
"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 earth-grounding. Review it before you use it.
Capability tags behind 7 rules
- mcp__earth-grounding__water_availability untrusted-input
- mcp__earth-grounding__seismic_hazard untrusted-input
- mcp__earth-grounding__ground_stability untrusted-input
- mcp__earth-grounding__resource_indication untrusted-input
- mcp__earth-grounding__space_weather_grid_risk untrusted-input
- mcp__earth-grounding__ground_truth untrusted-input
- mcp__earth-grounding__run_controlled_test 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.deepmapai/earth-grounding/verify?hash=3cbfeed8ce4bf9b13e62322db9995d97fe8da8c49dd8decc47c3e9325ee8d350" | jq -e '.changed == false'Pinned hash 3cbfeed8ce4b, from Nov 13, 2026, 01:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.deepmapai/earth-grounding/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.deepmapai/earth-grounding)Source: MCP Registry. Synced Oct 21, 2026, 17:54 UTC.
DeepMap AI -- Earth Grounding MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the DeepMap AI -- Earth Grounding MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 10 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the DeepMap AI -- Earth Grounding MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the DeepMap AI -- Earth Grounding 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 DeepMap AI -- Earth Grounding MCP server have?
- 11 tools: 10 write, 1 read. water_availability, seismic_hazard, ground_stability, resource_indication, space_weather_grid_risk, verify, ground_truth, capabilities and 3 more.
Does the DeepMap AI -- Earth Grounding MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the DeepMap AI -- Earth Grounding MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the DeepMap AI -- Earth Grounding MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Oct 31, 2026. Every change is on this page and in its Atom feed.