Umbra open SAR archive MCP Server
by reesehammerio.github.reesehammer/umbra-mcpv0.1.2
Search, preview, and measure Umbra open SAR from any MCP client. Umbra ships no search API.
context tax
queued
security
queued
cold start
queued
freshness
Active1d ago
Install Umbra open SAR archive MCP server
Install in Claude Code
claude mcp add umbra-py -e UMBRA_CANOPY_TOKEN='<umbra-canopy-token>' -e ANTHROPIC_API_KEY='<anthropic-api-key>' -e OPENAI_API_KEY='<openai-api-key>' -- uvx umbra-pyInstall in Cursor
{
"mcpServers": {
"umbra-py": {
"command": "uvx",
"args": [
"umbra-py"
],
"env": {
"UMBRA_CANOPY_TOKEN": "<umbra-canopy-token>",
"ANTHROPIC_API_KEY": "<anthropic-api-key>",
"OPENAI_API_KEY": "<openai-api-key>"
}
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"umbra-py": {
"command": "uvx",
"args": [
"umbra-py"
],
"env": {
"UMBRA_CANOPY_TOKEN": "<umbra-canopy-token>",
"ANTHROPIC_API_KEY": "<anthropic-api-key>",
"OPENAI_API_KEY": "<openai-api-key>"
}
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"umbra-py": {
"type": "stdio",
"command": "uvx",
"args": [
"umbra-py"
],
"env": {
"UMBRA_CANOPY_TOKEN": "<umbra-canopy-token>",
"ANTHROPIC_API_KEY": "<anthropic-api-key>",
"OPENAI_API_KEY": "<openai-api-key>"
}
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"umbra-py": {
"command": "uvx",
"args": [
"umbra-py"
],
"env": {
"UMBRA_CANOPY_TOKEN": "<umbra-canopy-token>",
"ANTHROPIC_API_KEY": "<anthropic-api-key>",
"OPENAI_API_KEY": "<openai-api-key>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Configuration
| Variable | Required | Secret | Description |
|---|---|---|---|
| UMBRA_CANOPY_TOKEN | — | yes | Canopy API token. Set it and the same search tools query Umbra's authenticated commercial archive instead of the open bucket; leave it unset for the open data, which needs no credentials. |
| UMBRA_INDEX_DB | — | — | Path to a local catalog index (built with 'umbra index build' or fetched with 'umbra index fetch'). Without one the server walks the public bucket per search, which is correct but slow. |
| ANTHROPIC_API_KEY | — | yes | Enables the two opt-in model tools, describe_scene and narrate_change. Every other tool is deterministic and calls no model. |
| OPENAI_API_KEY | — | yes | Alternative provider for the same two model tools, and the encoder behind find_similar_text. |
Freshness
Active — last maintenance signal 1d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-10-08 · 1d ago · GitHub
Latest release
2026-09-02 · 37d ago · GitHub · v0.1.2
Package published
no data · npm/PyPI
Registry entry updated
2026-09-02 · 37d ago · official registry · v0.1.2
FAQ
›How do I install the Umbra open SAR archive MCP server in Claude Code?
Run: claude mcp add umbra-py -e UMBRA_CANOPY_TOKEN='<umbra-canopy-token>' -e ANTHROPIC_API_KEY='<anthropic-api-key>' -e OPENAI_API_KEY='<openai-api-key>' -- uvx umbra-py. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Umbra open SAR archive require an API key?
Yes. It expects UMBRA_CANOPY_TOKEN, ANTHROPIC_API_KEY, OPENAI_API_KEY, of which 3 are secrets.
›Can I use Umbra open SAR archive as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is Umbra open SAR archive in the official MCP registry?
Yes, as io.github.reesehammer/umbra-mcp.