Skip to content

Deepmapai MCP server

Which MCP servers are Deepmapai's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-24

← Back to Deepmapai

Whose server it is
  • Registry namecom.deepmapai/earth-groundingverified in the MCP registry

The registry name sits under deepmapai.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-24
  • Stateanswerschecked 2026-10-24
  • Tools11
  • Server calls itselfdeepmap-earth-grounding-agent
  • Server version0.3.0
  • Protocol version2026-07-28

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 27 ms.

Should an agent connect itNot proven either way yet
  • Its tools do verify logged forecasts against the public ledger, but not receive alerts for chosen earthquake regions.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • For "verify logged forecasts against the public ledger", the likely first call is verify.
  • Parameters are untyped or undescribed in 10 of 11 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 4, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • What an agent can do with it1 of 2 use cases
  • Use59 PyPI downloads a week
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer95 ms
  • Space in an agent's context≈ 989 tokensthe definitions of all its tools (11), which an agent carries on every turn
  • Tool definitionsB · 85 of 100
  • Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 10 of 11

What an agent can do with it

  • not sure · check whether a city or postcode is on the watch
  • cannot · receive alerts for chosen earthquake regions
  • can do · verify logged forecasts against the public ledger

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers11 tools · read 2026-10-24
  • water_availability

    Water availability at a point. Free tier = public GRACE groundwater trend.

  • seismic_hazard

    Seismic hazard via the public, outcome-excluded prediction ledger (no platform-wide accuracy figure).

  • ground_stability

    Subsidence / void / karst / fault risk from verified observations.

  • resource_indication

    Geothermal / mineral / water indication (gated, honest null).

  • space_weather_grid_risk

    GIC / space-weather exposure for infrastructure at a point.

  • verify

    Verify a claim / the ledger hash chain against the Bitcoin-anchored record.

  • ground_truth

    The bundled five-question answer (water / stability / hazard / resource / provability) + one provenance record.

  • capabilities

    What DeepMap AI can answer now + coverage counts (public aggregate; tracks the library, leaks no proprietary data).

  • check_hypothesis

    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…

  • list_nulls

    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.

  • run_controlled_test

    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…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "earth-grounding": {
      "type": "http",
      "url": "https://deepmapai.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http deepmapai https://deepmapai.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://deepmapai.com/mcp as a custom connector in the settings.

Also shipped through: pypi

Other servers listed as Deepmapai's
  • com.deepmapai/geophysical-intelligencenot asked yetverified in the MCP registry

OpenAPI spec

3688 paths, read 2026-10-24. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.