PluginBench
MCP Server

Umbra open SAR archive MCP Server

io.github.reesehammer/umbra-mcp

RepositoryRegistry
How to choose

What this kind of tool is for

  • Let your agent search the web or a document set and cite what it found.
  • Pull structured facts out of pages instead of copy-pasting by hand.
  • Track changes on a topic over days without re-reading everything.

How to compare servers like this

Source coverage:
Check which engines, sites, or document types the tool can actually reach.
Citation behavior:
Prefer tools that return links you can open, not just summarized claims.
Terms of service:
Some sources forbid automated access; make sure the tool stays inside them.
Maintenance signal:
Scrapers break silently when pages change; recent commits are the best proxy.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the Umbra open SAR archive MCP server?

Search, preview, and measure Umbra open SAR from any MCP client. Umbra ships no search API.

How to install Umbra open SAR archive

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • UMBRA_CANOPY_TOKEN
    secret

    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
    secret

    Enables the two opt-in model tools, describe_scene and narrate_change. Every other tool is deterministic and calls no model.

  • OPENAI_API_KEY
    secret

    Alternative provider for the same two model tools, and the encoder behind find_similar_text.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "umbra-mcp": {
      "command": "uvx",
      "args": [
        "umbra-py",
        "--from",
        "umbra-py[mcp]",
        "umbra-mcp"
      ],
      "env": {
        "UMBRA_CANOPY_TOKEN": "<YOUR_UMBRA_CANOPY_TOKEN>",
        "UMBRA_INDEX_DB": "<YOUR_UMBRA_INDEX_DB>",
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

Related MCP servers

Search curated design styles, real product screens, and user flows for evidence-based design work.

Search 93M+ tracks, artists, and releases: metadata, ISRC/ISWC, and cross-platform IDs for AI.

0
TypeScript
MIT
View repository →

Run Sherlock, Maigret, Holehe, GHunt, theHarvester, SpiderFoot and more OSINT tools locally

0
Python
MIT
View repository →
REResearch MCP logo

Cited research MCP (MCP+agent infra): brief, lookup. Fail=$0.

0
TypeScript
MIT
View repository →

Token-efficient documentation search for AI coding agents over public and private resources.

1.2k
TypeScript
MIT
View repository →

Model Context Protocol server for Refgrow affiliate program management API

2
TypeScript
View repository →