Elevation MCP Server

@cyanheads/elevation-mcp-server Look up elevation worldwide, profile route ascent/descent, grid areas, check terrain line of sight via MCP. STDIO or Streamable HTTP. 4 Tools

Public Hosted Server: https://elevation.caseyjhand.com/mcp

Overview

Elevation and terrain analysis anywhere on Earth, from USGS 3DEP (1–30 m across the US) and Open Topo Data worldwide. Look up spot heights, measure a route's climbs and grades, find an area's high and low points, and check whether terrain blocks a line of sight. No API key required.

Tools

Agent skill

The elevation-guide covers route geometry, candidate high-point refinement, and visual or radio sightline assessment. Plugin installs discover it in root skills/; npm, Docker, and MCPB distributions include it. MCP clients can read skill://elevation-guide/SKILL.md as a resource or use the Skills extension.

Capability reference

Every successful result includes vertical_reference on both response surfaces. Public SRTM uses EGM96; NAVD88 is typical for 3DEP in the conterminous US, but the returned raster reference is unverified and can vary elsewhere. Mapzen and self-hosted Open Topo Data references are unknown/variable. No-data-only results establish no height reference. Heights are returned without transformation; mixed datasets are not normalized to a common datum. water_surface_m needs a compatible terrain reference; zero or source: opentopodata alone does not establish compatibility.

elevation_get_points tool

• points: 1–1,000 {lat, lon} objects in decimal degrees (WGS84), or a single point. Only the first 100 are validated and sampled; the remainder stays unvalidated
• requested_points, processed_points, and remaining_points count submitted positions, including duplicates and misses. next_offset is the index after this call's processed prefix, or null when exhausted; continue with originalPoints.slice(next_offset), where originalPoints is the array submitted in that call. Use each newly submitted array for the next slice
• Each point comes back ok or no_data (a miss never fails the call), with elevation_m / elevation_ft, dataset, and resolution_m (omitted for mapzen); 3DEP answers add raster_id and acquisition_date. points_with_data counts the hits

elevation_get_profile tool

• path: 2–1,000 vertices in travel order (consecutive duplicates dropped); samples: 2–250 evenly spaced points along it, endpoints included (default 100)
• summary carries total_distance_m, ascent_m / descent_m (and feet), start, end, min, and max elevation, highest_point / lowest_point, and max_grade_pct / min_grade_pct with where each occurs; ascent depends on the reported sample_interval_m. Fails as degenerate_path (under 1 m of route), antipodal_path (add an intermediate waypoint between the identified zero-based input vertices), or no_coverage (no sample has data)
• include_samples (default true) returns samples[] (distance, position, elevation, grade, dataset, and resolution per sample); false omits it and the sample table, and the rest of the result is unchanged

elevation_get_grid tool

• south, west, north, east edges in decimal degrees (a box can't cross longitude 180); rows and cols 2–25 each (default 10), with rows × cols at most 250
• elevations_m and cell_datasets matrices indexed row (row 0 north, column 0 west, null without data), plus summary.highest, summary.lowest, mean_elevation_m, and relief_m. Fails as invalid_bbox, too_many_cells, or no_coverage
• Nodes are point samples with the edges included, not cell averages

elevation_check_line_of_sight tool

• observer and target points, at most 1,000 km apart; observer_height_m (default 1.7) and target_height_m (default 0), each 0–10,000 m above ground; earth_model flat, geometric, optical (default, κ 0.13), or radio (κ 0.25); samples 3–250 (default 100); optional water_surface_m (-500 to 9,000) and frequency_mhz (30–300,000)
• verdict is clear, blocked, or indeterminate (samples without data leave the line unconfirmed), with min_clearance_m / min_clearance_ft, the limiting_point, and the first_obstruction when blocked. Fails as same_endpoints (under 1 m apart), sightline_too_long (over 1,000 km apart), or endpoint_no_data
• frequency_mhz adds fresnel: a sufficient, insufficient, or indeterminate verdict against the 60% free-space bar of the first Fresnel zone, min_clearance_ratio (clearance over zone radius), and the sample that limits it, which is often not limiting_point
• Terrain only: buildings and vegetation count only as far as the elevation source captures them. Where Mapzen reports sea-floor depth, clearance is measured to the sea surface; USGS 3DEP values below 0 m (bay floor in some bays, or dry land) count as received unless water_surface_m sets a water level, which then applies to every sample

Failures shared by every tool

A coverage miss is never an error: that point has no data. Any provider failure fails the whole call with no partial result.

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Elevation-specific:

• source on every tool: auto (default) queries USGS 3DEP inside its coverage and sends 3DEP misses and everything outside it to Open Topo Data; usgs_3dep and opentopodata pin one provider. Only a coverage miss falls back, never an outage
• Open Topo Data answers from SRTM GL1 v3 (about 30 m, land between 60°N and 56°S), then Mapzen terrain tiles where SRTM has no tile: high latitudes, Antarctica, and ocean bathymetry
• Per-call caps of 100 points or 250 samples or grid cells, inside a 45 s sampling budget; each 3DEP point is its own request (6 concurrent, 10 per second), while Open Topo Data takes 100 points per request
• The public Open Topo Data instance is paced under its published limits: one request at a time, starts at least 1.1 s apart, at most 1,000 in any trailing 24 hours per server process
• Profiles, grids, and sightlines are computed locally from point samples, with great-circle distances and resampling and earth curvature with standard refraction

Agent-friendly output:

• Provenance on every value: each point, profile sample, grid cell, and sightline point names its dataset (usgs_3dep, srtm30m, mapzen) and, except for Mapzen, its resolution_m (resolution_m_range on profiles and grids); computed results add datasets_used counts, and a Sources: line credits every dataset that answered
• Absent stays absent: a point or sample without data omits its elevation and a grid cell is null, never 0; summaries report how many values had data
• Notices flag what changes interpretation: results mixing 3DEP and Open Topo Data, Mapzen values below 0 m (sea-floor depths), 3DEP values below 0 m on a sightline, sample spacing coarser or finer than the source, thin clearance margins, and a clear radio path short of 60% Fresnel clearance

Getting started

Connect to the public instance:

claude mcp add --transport http elevation-mcp-server https://elevation.caseyjhand.com/mcp

Every hosted caller shares one Open Topo Data allowance of 1,000 requests a day. Under auto, 3DEP answers inside its coverage and Open Topo Data handles the rest. For sustained global use, run your own instance:

claude mcp add elevation-mcp-server -- npx -y @cyanheads/elevation-mcp-server

Other MCP clients use this local configuration:

`json