GeoEDGE MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 348 installs a week from pypi.
Geospatial analysis: vector and raster GIS operations, cartographic maps, spatial data access
Today is the operative word: we check GeoEDGE MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add geoedge-mcp -e 'GEOEDGE_MCP_LICENSE_KEY=<GEOEDGE_MCP_LICENSE_KEY>' -- uvx geoedge-mcp
{
"mcpServers": {
"geoedge-mcp": {
"command": "uvx",
"args": [
"geoedge-mcp"
],
"env": {
"GEOEDGE_MCP_LICENSE_KEY": "<GEOEDGE_MCP_LICENSE_KEY>"
}
}
}
}
[mcp_servers.geoedge-mcp]
command = "uvx"
args = ["geoedge-mcp"]
env = { GEOEDGE_MCP_LICENSE_KEY = "<GEOEDGE_MCP_LICENSE_KEY>" }
{
"mcpServers": {
"geoedge-mcp": {
"command": "uvx",
"args": [
"geoedge-mcp"
],
"env": {
"GEOEDGE_MCP_LICENSE_KEY": "<GEOEDGE_MCP_LICENSE_KEY>"
}
}
}
}
{
"servers": {
"geoedge-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"geoedge-mcp"
],
"env": {
"GEOEDGE_MCP_LICENSE_KEY": "<GEOEDGE_MCP_LICENSE_KEY>"
}
}
}
}
Put your own value in place of
<GEOEDGE_MCP_LICENSE_KEY> (GeoEDGE subscription licence key (see https://mcp.geoedge.com.au). GIS tools are disabled without it).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
GEOEDGE_MCP_STORAGE_PATH (Optional folder where GeoEDGE-MCP reads and writes GIS data files. Defaults to a per-user folder).
A collaborative substrate over your data: vector, knowledge graph, SQL, geospatial, streaming.
31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.
Create and manage vector database indexes, backups, and collections
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Knowledge synthesis MCP server with vector-deduplicated lessons and x402 micropayments.
Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.
Answers built from our own checks of this server.