elevation-mcp-server

Get Elevation Grid

elevation_get_grid

Read-onlyIdempotent

Sample a regular grid of terrain elevations across a bounding box and report the highest and lowest sampled points, the mean elevation, and the relief, plus the full elevation matrix with each cell's dataset. Values are point samples at grid nodes (box edges included), not cell averages, so a summit between nodes is missed; to refine a candidate high or low point, call again with a smaller box around it. Over open water, Mapzen cells are sea-floor depths. Rows times columns may not exceed 250.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cols`	No	Grid columns, west to east, edges included (2–25, default 10). rows × cols must be at most 250.
`east`	Yes	Eastern edge longitude, decimal degrees.
`rows`	No	Grid rows, north to south, edges included (2–25, default 10). rows × cols must be at most 250.
`west`	Yes	Western edge longitude, decimal degrees. Must be less than east; a box crossing longitude 180 must be split into two calls.
`north`	Yes	Northern edge latitude, decimal degrees. Must be greater than south.
`south`	Yes	Southern edge latitude, decimal degrees.
`source`	No	Elevation source: auto (default) uses USGS 3DEP where it has data and Open Topo Data (SRTM, with Mapzen terrain tiles where SRTM has no data) for the rest; usgs_3dep uses 3DEP only; opentopodata uses Open Topo Data only. Case is ignored and spaces or hyphens read as underscores, so USGS-3DEP and open topo data are accepted; 3dep, usgs, and epqs are also aliases for usgs_3dep.	auto

Output Schema

TableJSON Schema

Name	Required	Description
`cols`	No	Node columns applied.
`east`	No	Eastern edge longitude, as requested.
`rows`	No	Node rows applied.
`west`	No	Western edge longitude, as requested.
`error`	No	Present when the call failed. Absent on success.
`north`	No	Northern edge latitude, as requested.
`south`	No	Southern edge latitude, as requested.
`notice`	No	Guidance on nodes without data, boxes spanning the USGS 3DEP coverage edge, Mapzen sea-floor values, and node spacing against the source resolution.
`summary`	No	Statistics over the nodes with data.
`attribution`	No	Sources to credit for the returned values, one line per dataset that answered.
`source_mode`	No	The source the call used (auto unless the caller chose one).
`elevations_m`	No	Elevation matrix indexed [row][col], rows north to south, columns west to east.
`cell_datasets`	No	Provenance matrix with the same [row][col] indexing as elevations_m.
`col_spacing_m`	No	East-west distance between node columns at the box's center latitude, meters.
`datasets_used`	No	Number of values each dataset answered.
`latitudes_deg`	No	Latitude of each row, north to south; row 0 is the north edge.
`missing_cells`	No	Nodes no queried dataset answered.
`row_spacing_m`	No	North-south distance between node rows, meters.
`longitudes_deg`	No	Longitude of each column, west to east; column 0 is the west edge.
`cells_with_data`	No	Nodes with an elevation.
`resolution_m_range`	No	Range of source resolutions over values that report one; absent when none does (all Mapzen).
`vertical_reference`	No	Height-reference context per answering dataset, including unverified references and whether heights share a datum. No vertical datum conversion is performed.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 18, 2026

changedOutput schema / anyOf

Previous value: -[
-  {
-    "not": {
-      "required": [
-        "error"
-      ]
-    },
-    "required": [
-      "south",
-      "west",
-      "north",
-      "east",
-      "rows",
-      "cols",
-      "latitudes_deg",
-      "longitudes_deg",
-      "row_spacing_m",
-      "col_spacing_m",
-      "elevations_m",
-      "cell_datasets",
-      "summary",
-      "cells_with_data",
-      "missing_cells",
-      "datasets_used",
-      "source_mode",
-      "attribution"
-    ]
-  },
-  {
-    "required": [
-      "error"
-    ]
-  }
-]New value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "south",
+      "west",
+      "north",
+      "east",
+      "rows",
+      "cols",
+      "latitudes_deg",
+      "longitudes_deg",
+      "row_spacing_m",
+      "col_spacing_m",
+      "elevations_m",
+      "cell_datasets",
+      "summary",
+      "cells_with_data",
+      "missing_cells",
+      "datasets_used",
+      "source_mode",
+      "vertical_reference",
+      "attribution"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / vertical_reference

Added value: +{
+  "description": "Height-reference context per answering dataset, including unverified references and whether heights share a datum. No vertical datum conversion is performed.",
+  "type": "string"
+}

First observedOct 2, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent/openWorld annotations, it discloses key behavioral traits: values are point samples at grid nodes (edges included), not cell averages; summits between nodes can be missed; Mapzen cells over open water are sea-floor depths; and the 250-cell cap. These are exactly the subtleties an agent needs and are not in the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then limitations, then the size cap — each sentence earns its place. It is dense but not padded; slight redundancy between the description's 250 limit and the same constraint already in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not explain return values, and it covers the sampling semantics, source behavior, and limits an agent needs to invoke this correctly across a bounding box.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, but the description adds interpretive meaning: what grid-node sampling implies for rows/cols and that over-water cells return depths rather than elevations. It does not add much beyond the strongly documented schema, so a 4 rather than 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Sample a regular grid of terrain elevations across a bounding box') and enumerates what is reported (high/low, mean, relief, full matrix). This clearly differentiates it from siblings like get_points, get_profile, and check_line_of_sight, which are not grid-based.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives actionable guidance — refine a candidate high/low point by calling again with a smaller box — and explains the point-sample limitation that motivates it. It does not explicitly name the sibling tools or state when to prefer them over this one, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All elevation-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.