Anchors physical-world ground-truth claims and ledger hash chains to Bitcoin, enabling verifiable provenance records that can be checked against a public Bitcoin-anchored ledger.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Earth Grounding MCP Check water availability at 34.05,-118.24 and verify the provenance."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Verifiable physical-world ground truth for AI agents. Ask about subsurface water, seismic and space-weather hazard, ground stability, and resource indications for any point on Earth — and every answer carries a Bitcoin-anchored provenance record, so a physical-world claim can be checked rather than trusted.
This repository holds the published thin client: a small stdio
Model Context Protocol server that proxies your calls to
DeepMap's hosted engine at https://deepmapai.com/mcp. It is stdlib-only — no
dependencies, no platform code, no proprietary data. The answers and their provenance come
from the hosted service.
Registry id: com.deepmapai/earth-grounding
Hosted endpoint: https://deepmapai.com/mcp (Streamable HTTP)
Public ledger: https://deepmapai.com/track-record
uvx deepmap-earth-grounding-mcpA free demo key works with no signup:
export DEEPMAP_API_KEY=demo-freeClaude Code, hosted (no install):
claude mcp add --transport http deepmap-earth-grounding https://deepmapai.com/mcp --header "apiKey: demo-free"Claude Code, local stdio:
claude mcp add deepmap-earth-grounding -e DEEPMAP_API_KEY=demo-free -- uvx deepmap-earth-grounding-mcpPer-client config snippets (Claude Desktop, Cursor, VS Code, generic) are in
connectors/; see INSTALL.md.
Related MCP server: groundstation
Eight answer questions about a place. Three answer questions about the evidence itself — those are the ones worth reading twice.
tool | what it answers |
| replenishable-water availability at a point |
| seismic hazard via the public, outcome-excluded prediction ledger |
| subsidence / void / karst / fault risk from verified observations |
| geothermal / mineral / gas / water indication (gated) |
| live geomagnetic (Kp) activity as GIC / grid exposure |
| verify a claim hash / the ledger hash chain against the Bitcoin anchor |
| the bundled five-question answer + one provenance record |
| what DeepMap can answer now + public coverage counts |
| has this Earth-science hypothesis already been tested? Queries the Null Museum and the anchored hypothesis registry, and returns the verdict with the positive control that proves the test was sensitive |
| the documented nulls, bounds and retractions — we carry our own, and that is the point |
| Lab-as-an-API: fetches real data, runs a bounded controlled test with a local-background null and a positive control, and returns |
Grounded on a geophysical sensor network and live feeds, not on the open web.
Verifiable — answers reference a Bitcoin-anchored, pre-registered ledger. Call
verify on any claim hash and check it yourself.
Honest by construction — it returns null rather than a fabricated value, publishes
no platform-wide accuracy headline, and will tell you a question is UNTESTABLE instead
of inventing a clean answer. A negative result is only worth anything next to the
positive control that shows the test could have detected something; both are returned.
tools/list is answered locally, so the tool surface is visible offline and without a
key. tools/call is proxied to the hosted endpoint with your apiKey. If the endpoint is
unreachable the client returns an honest tool error rather than crashing — and never a
substituted value.
Run the self-test:
python -m deepmap_earth_mcp --self-testinfo@deepmapai.com · service terms: https://deepmapai.com/terms
What DeepMap can answer now + coverage counts (public aggregate).
Inputs: no named parameters.
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.
Inputs: claim (required), limit, domain.
Subsidence / void / karst / fault risk from verified observations.
Inputs: lat (required), lon (required), radius_km.
The bundled five-question answer + one provenance record.
Inputs: lat (required), lon (required).
List DeepMap'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.
Inputs: limit, domain.
Geothermal / mineral / gas / water indication (gated, low-confidence).
Inputs: lat (required), lon (required), type.
The Lab-as-an-API: run a REAL, bounded controlled test at a location and get an honest verdict. DeepMap 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). Free tier runs a synthetic demo; the live lab is the authenticated tier.
Inputs: lat, lon, observable.
Seismic hazard via the public, outcome-excluded prediction ledger.
Inputs: lat (required), lon (required), region, horizon_days.
Live geomagnetic activity (Kp) as GIC / space-weather grid exposure.
Inputs: lat (required), lon (required).
Verify a claim hash / the ledger hash chain against the Bitcoin anchor.
Inputs: claim_hash.
Replenishable-water availability at a point. Free = public groundwater trend; paid adds a derived (non-locating) atlas indication.
Inputs: lat (required), lon (required), depth_m.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 11 tools
The hazard tools (water_availability, seismic_hazard, ground_stability, space_weather_grid_risk) each target a distinct exposure with clear boundaries. However, resource_indication explicitly covers 'water' and overlaps with water_availability, which could cause misselection, and the meta tools (ground_truth, capabilities, check_hypothesis) require careful reading to distinguish 'answer now' vs 'registry query'.
All names use snake_case, which is consistent. There is a minor stylistic split between bare domain nouns (seismic_hazard, ground_stability, capabilities) and verb_noun action names (check_hypothesis, list_nulls, run_controlled_test, verify), but each name is readable and predictable.
11 tools is well within the sweet spot for a domain server and each tool appears to earn its place across hazard lookups, verification, and the hypothesis/null registry.
The surface covers a broad lifecycle: query geohazard data, verify provenance/anchors, test hypotheses, list nulls, and run controlled tests. There is no obvious create/update flow, but for a read-oriented ground-truth service this is close to complete; minor gaps are workable.
Verifiable Earth ground truth for AI agents: water, hazard, ground stability, resource, with proof.
Free verified network knowledge for AI agents: deterministic answers, honest unknowns.
Deterministic fact verification for AI agents — checksums & curated data, not guesses.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
