Ir al contenido
getgeolens.com

MCP Server

Esta página aún no está disponible en tu idioma.

The GeoLens MCP server (geolens-mcp) is a read-only Model Context Protocol server. Point a coding agent (Claude Code, Cursor, Codex, and any other MCP client) at a GeoLens instance and it can discover datasets, inspect schemas, and read features and maps from inside a dev session. It is Apache-2.0 licensed and built on the Python SDK, so every tool maps to a real endpoint in the API reference.

Terminal window
pip install geolens-mcp # or: uvx geolens-mcp

uvx runs the server without a persistent install, which is what the client-registration examples below use.

The server reads its target instance and credentials from the environment — the same variable names the CLI uses:

VariableRequiredMeaning
GEOLENS_INSTANCEYesInstance URL, e.g. https://geolens.example.com. The /api suffix is appended automatically if you omit it.
GEOLENS_API_KEYRecommendedAPI key, sent as X-Api-Key. Omit for public-only access. See Authentication → API keys for how to obtain one.
GEOLENS_TOKENJWT bearer token, used only if GEOLENS_API_KEY is unset.

Claude Code — one command registers the server for the current project:

Terminal window
claude mcp add geolens \
-e GEOLENS_INSTANCE=https://geolens.example.com \
-e GEOLENS_API_KEY=... \
-- uvx geolens-mcp

Cursor, Codex, or any client that reads an mcpServers block:

{
"mcpServers": {
"geolens": {
"command": "uvx",
"args": ["geolens-mcp"],
"env": {
"GEOLENS_INSTANCE": "https://geolens.example.com",
"GEOLENS_API_KEY": "your-api-key"
}
}
}
}
ToolWhat it does
search_datasetsCatalog search by free text (semantic ranking where the instance enables it). Returns dataset records as GeoJSON features.
get_dataset_schemaA dataset’s columns, geometry type, CRS/SRID, feature count, and extent.
get_featuresBounded GeoJSON features for a dataset (OGC API — Features), with optional bbox.
list_mapsSaved maps (id, name, visibility, layer count).
get_mapOne saved map’s full metadata, including layers and view state.

A query tool — running SQL through GeoLens’s read-only sandbox — is intentionally not in this release. The sandbox has no direct REST endpoint today, and exposing raw SQL over HTTP needs security hardening (cost/DoS bounds, rate limiting, mandatory dataset scope) before it is safe to point at a production instance. Follow geolens#565 for progress.

  • Client SDKs: the Python SDK that geolens-mcp builds on, and the CLI-vs-SDK-vs-MCP-vs-API decision table
  • CLI & Manifests: the same credential/instance environment variables, for terminal and CI ingestion
  • API Authentication: JWT and API-key details for the credentials above
  • Search & Discovery: what search_datasets returns, including semantic ranking