E
edkearth/mcp
EDK-1 is a foundation model of the physical world.
updated 2026-11-15
View on GitHub ↗Direct link · no redirect page
We have no copy-paste install command and no public remote endpoint, so we do not print a config. The step above is reference only, not a command we can vouch for. A made-up one is worse than none. How each client wires MCP up →
- Star count
- 0 ★ · edkearth/mcp · read from the GitHub search API · (checked 2026-11-19 20:00:48)
- Source
- collected from the punkpeye/awesome-mcp-servers list · type: MCP server
- Harvest history
- first seen 2026-11-18 · last seen 2026-11-20 · seen 3× · listed by 3 sources
- Score
- score 300 · 3 sources · mcp
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: MCP servers. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
edkearth/mcp;first catalogued 2026-11-18;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.README excerpt (English, untranslated) · Read the full README on GitHub →
# EDK-1 MCP server
Excerpted from the repository README (abridged)
EDK-1 is a foundation model of the physical world. Trained on 30 billion images, it sees the planet street by street, so your agent can find anything visible on Earth, read what's true there, route around it, and get alerted the moment it changes.
Use EDK when a task depends on what the real world looks like.
"Streetlight issues in New Orleans where median household income is under $40k"
"Vandalism in Chicago on blocks where most homes are rented"
"Cyclist accidents in Chicago where over 10% of people walk or bike to work"
"Cracked asphalt in Sacramento inside flood zones"
"Desert wildflower blooms in California where annual rainfall is under 200 mm"
"Fern-filled forests in New Zealand where annual rainfall is over 2,000 mm"
"Bison herds in South Dakota more than an hour from a city"
"Accessory dwelling unit permits in Los Angeles where median home value is over $1M"
"New building permits in New York City inside flood zones"
Every result comes back with its location, its photo and an embed_url that opens it on the EDK Atlas.
## Tools
| Tool | What it does |
| edk_discover | Ask for objects (graffiti, solar panels, bridges), conditions (storm-damaged roofs, boarded-up windows, potholes), events (crashes, new construction) or nature (humpback whales, alligators, wildflowers), and get each one back with its photo. Or find areas by what's measured there, like flood risk, income or tree canopy. Set reasoning from fast to max to have results studied more closely. |
| edk_inspect | Read what's true at any coordinate, from terrain and hazards to who lives there. |
| edk_route | Get from A to B around what you name, like potholed streets, construction or crash-prone intersections. |
| edk_monitor_create | Watch a place and get each new sighting by webhook. |
| edk_monitor_events | List monitors and the events they found. |
| edk_usage | Compute Unit balance, tier and limits. |
## Setup
1. Sign up at edk.earth. Every account gets 500 free Compute Units a month.
2. Create a secret key in Console → API Keys.
3. Add the server to your client with EDK_API_KEY set.
Claude Code
sh
claude mcp add edk --env EDK_API_KEY=edk_sk_... -- npx -y @edks/mcp
Claude Desktop (claude_desktop_config.json), Cursor (.cursor/mcp.json), Windsurf and Gemini CLI (~/.gemini/settings.json)
json
"mcpServers": {
"edk": {
"command": "npx",
"args": ["-y", "@edks/mcp"],
"env": { "EDK_API_KEY": "edk_sk_..." }
VS Code (.vscode/mcp.json)
json
"inputs": [{ "type": "promptString", "id": "edk-key", "description": "EDK API key", "password": true }],
Use EDK when a task depends on what the real world looks like.
"Streetlight issues in New Orleans where median household income is under $40k"
"Vandalism in Chicago on blocks where most homes are rented"
"Cyclist accidents in Chicago where over 10% of people walk or bike to work"
"Cracked asphalt in Sacramento inside flood zones"
"Desert wildflower blooms in California where annual rainfall is under 200 mm"
"Fern-filled forests in New Zealand where annual rainfall is over 2,000 mm"
"Bison herds in South Dakota more than an hour from a city"
"Accessory dwelling unit permits in Los Angeles where median home value is over $1M"
"New building permits in New York City inside flood zones"
Every result comes back with its location, its photo and an embed_url that opens it on the EDK Atlas.
## Tools
| Tool | What it does |
| edk_discover | Ask for objects (graffiti, solar panels, bridges), conditions (storm-damaged roofs, boarded-up windows, potholes), events (crashes, new construction) or nature (humpback whales, alligators, wildflowers), and get each one back with its photo. Or find areas by what's measured there, like flood risk, income or tree canopy. Set reasoning from fast to max to have results studied more closely. |
| edk_inspect | Read what's true at any coordinate, from terrain and hazards to who lives there. |
| edk_route | Get from A to B around what you name, like potholed streets, construction or crash-prone intersections. |
| edk_monitor_create | Watch a place and get each new sighting by webhook. |
| edk_monitor_events | List monitors and the events they found. |
| edk_usage | Compute Unit balance, tier and limits. |
## Setup
1. Sign up at edk.earth. Every account gets 500 free Compute Units a month.
2. Create a secret key in Console → API Keys.
3. Add the server to your client with EDK_API_KEY set.
Claude Code
sh
claude mcp add edk --env EDK_API_KEY=edk_sk_... -- npx -y @edks/mcp
Claude Desktop (claude_desktop_config.json), Cursor (.cursor/mcp.json), Windsurf and Gemini CLI (~/.gemini/settings.json)
json
"mcpServers": {
"edk": {
"command": "npx",
"args": ["-y", "@edks/mcp"],
"env": { "EDK_API_KEY": "edk_sk_..." }
VS Code (.vscode/mcp.json)
json
"inputs": [{ "type": "promptString", "id": "edk-key", "description": "EDK API key", "password": true }],
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/edkearth-mcp/)
- Source
- awesome · https://github.com/edkearth/mcp
- Browse by field
- MCP servers
- Listed by
- 3 independent sources
- added
- today
More MCP servers
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.