# EmbedEarth MCP server

> Provides AI agents with tools for geographic search, spatial computation, routing, mapping, and managing geographic datasets.

- Repository: https://github.com/embedearth/e2
- Page: https://hostedmcp.org/servers/embedearth/mcp
- Transport: stdio
- Stars: 1
- License: Apache-2.0
- Latest version: 0.1.18

## Install

### Claude Code

```sh
claude mcp add --env 'E2_API_KEY=<YOUR_E2_API_KEY>' mcp -- npx -y @embedearth/mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@embedearth/mcp"
      ],
      "env": {
        "E2_API_KEY": "<YOUR_E2_API_KEY>"
      }
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@embedearth/mcp"
      ],
      "env": {
        "E2_API_KEY": "<YOUR_E2_API_KEY>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@embedearth/mcp"],"env":{"E2_API_KEY":"<YOUR_E2_API_KEY>"}}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@embedearth/mcp"
      ],
      "env": {
        "E2_API_KEY": "<YOUR_E2_API_KEY>"
      }
    }
  }
}
```

### Codex

```sh
codex mcp add mcp --env 'E2_API_KEY=<YOUR_E2_API_KEY>' -- npx -y @embedearth/mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@embedearth/mcp"]

[mcp_servers.mcp.env]
E2_API_KEY = "<YOUR_E2_API_KEY>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'E2_API_KEY=<YOUR_E2_API_KEY>' mcp npx -- -y @embedearth/mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@embedearth/mcp"
      ],
      "env": {
        "E2_API_KEY": "<YOUR_E2_API_KEY>"
      }
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `E2_API_KEY` | no | yes | Optional EmbedEarth API key from embed.earth. Raises Cloud Search, Compute, and Route limits from 60 to 2,000 requests per minute and is required for street-level imagery. |
| `ROUTE_URL` | no | no | Optional URL of a custom routing service compatible with the E2 route API. Defaults to the first-party routing endpoint. |

## FAQ

### What modes does EmbedEarth support?

E2 can run in auto, offline, or cloud modes. Local datasets are downloaded once per region and reused for future requests.

### What kind of spatial analysis can I perform?

You can find nearest features, measure distances, count features, calculate density and coverage, detect gaps, or cluster nearby objects.

### How can I use EmbedEarth for routing?

You can route between coordinates, calculate travel-time matrices, generate isochrones, or perform map matching.
