protogrid
Sign inAdd to your agent

Search / io.github.reesehammer/umbra-mcp

Umbra open SAR archive

L0· runs locally

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

v0.1.3 · active · repository · descriptor JSON · versions

Runs on your machine: something must execute the package.Only local packages are published (npm, PyPI, OCI, …). The registry never executes them, so tools are unknown until you run it.
Quality–not scored
Trust91of 100
Packages1
Tools seen0

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "umbra-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "umbra-py[mcp]",
        "umbra-mcp",
        "umbra-py==0.1.3"
      ],
      "env": {
        "UMBRA_CANOPY_TOKEN": "${UMBRA_CANOPY_TOKEN}",
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}
claude mcp add umbra-mcp -e "UMBRA_CANOPY_TOKEN=${UMBRA_CANOPY_TOKEN}" -e "ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}" -e "OPENAI_API_KEY=${OPENAI_API_KEY}" -- uvx --from umbra-py[mcp] umbra-mcp umbra-py==0.1.3
[mcp_servers.umbra-mcp]
command = "uvx"
args = ["--from", "umbra-py[mcp]", "umbra-mcp", "umbra-py==0.1.3"]
env = { "UMBRA_CANOPY_TOKEN" = "${UMBRA_CANOPY_TOKEN}", "ANTHROPIC_API_KEY" = "${ANTHROPIC_API_KEY}", "OPENAI_API_KEY" = "${OPENAI_API_KEY}" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "umbra-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "--from",
        "umbra-py[mcp]",
        "umbra-mcp",
        "umbra-py==0.1.3"
      ],
      "enabled": true,
      "environment": {
        "UMBRA_CANOPY_TOKEN": "{env:UMBRA_CANOPY_TOKEN}",
        "ANTHROPIC_API_KEY": "{env:ANTHROPIC_API_KEY}",
        "OPENAI_API_KEY": "{env:OPENAI_API_KEY}"
      }
    }
  }
}
{
  "mcpServers": {
    "umbra-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "umbra-py[mcp]",
        "umbra-mcp",
        "umbra-py==0.1.3"
      ],
      "env": {
        "UMBRA_CANOPY_TOKEN": "${UMBRA_CANOPY_TOKEN}",
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=umbra-mcp&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb20iLCJ1bWJyYS1weVttY3BdIiwidW1icmEtbWNwIiwidW1icmEtcHk9PTAuMS4zIl0sImVudiI6eyJVTUJSQV9DQU5PUFlfVE9LRU4iOiIke1VNQlJBX0NBTk9QWV9UT0tFTn0iLCJBTlRIUk9QSUNfQVBJX0tFWSI6IiR7QU5USFJPUElDX0FQSV9LRVl9IiwiT1BFTkFJX0FQSV9LRVkiOiIke09QRU5BSV9BUElfS0VZfSJ9fQ%3D%3D"
}
{
  "servers": {
    "umbra-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "umbra-py[mcp]",
        "umbra-mcp",
        "umbra-py==0.1.3"
      ],
      "env": {
        "UMBRA_CANOPY_TOKEN": "${UMBRA_CANOPY_TOKEN}",
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}
{
  "mcpServers": {
    "umbra-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "umbra-py[mcp]",
        "umbra-mcp",
        "umbra-py==0.1.3"
      ],
      "env": {
        "UMBRA_CANOPY_TOKEN": "${UMBRA_CANOPY_TOKEN}",
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}
extensions:
  "umbra-mcp":
    enabled: true
    name: "umbra-mcp"
    type: stdio
    cmd: "uvx"
    args:
      - "--from"
      - "umbra-py[mcp]"
      - "umbra-mcp"
      - "umbra-py==0.1.3"
    envs:
      "UMBRA_CANOPY_TOKEN": "${UMBRA_CANOPY_TOKEN}"
      "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}"
      "OPENAI_API_KEY": "${OPENAI_API_KEY}"
    timeout: 300

Placeholders to fill from your own secret store: ${UMBRA_CANOPY_TOKEN}, ${ANTHROPIC_API_KEY}, ${OPENAI_API_KEY}. The registry never accepts secret values.

This is a local package: the command runs on your machine.

Quality – / 100not scored

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

protocoln/a · weight 25
  • n/a
    protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygienen/a · weight 30
  • n/a
    tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool list unknown
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledeps.dev does not know [email protected]

Tool list unknown · checked 2026-10-20 13:49 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 91 / 100

provenance80
livenessn/a
freshness100
hygiene100

+repository +namespace-matches-repo ~liveness-unmeasured +updated-4d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

[email protected] PyPIthis version is not known to the dependency resolver

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

packageregistryversionruntimesecrets
umbra-pypypi0.1.3uvxUMBRA_CANOPY_TOKEN, ANTHROPIC_API_KEY, OPENAI_API_KEY

Tools (0)

No tools observed. Local packages are never executed by the registry.

Schemas: list_tools.

Similar MCP servers

  • archlinux-mcpL0
    io.github.mrfentmen/archlinux-mcp

    Arch Linux package search API.

  • mcp-unifi-applicationsL0
    io.github.KallistoX/mcp-unifi-applications

    Queryable UniFi API docs: endpoint search, schemas, code examples. No controller access.

  • Agora by openforallofusR0quality 92
    com.openforallofus/agora

    Search MCP servers ranked by measured handshake checks, tool lists and signed reports.

  • Mdn SearchR0
    io.github.pipeworx-io/mdn-search

    MDN Search MCP

  • Open QualityR0quality 88
    us.openquality/mcp

    Open healthcare quality measures: CQL, SQL and FHIR with provenance and known issues

  • CensysR0
    io.github.pipeworx-io/censys

    Censys MCP — internet-scan search over the Censys Platform API (censys.com)

Official server.json
{
  "name": "io.github.reesehammer/umbra-mcp",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "command": "uvx --from 'umbra-py[mcp]' umbra-mcp",
      "documentation": "https://github.com/reesehammer/umbra-py#drive-it-from-an-ai-agent-mcp"
    }
  },
  "title": "Umbra open SAR archive",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "version": "0.1.3",
  "packages": [
    {
      "version": "0.1.3",
      "transport": {
        "type": "stdio"
      },
      "identifier": "umbra-py",
      "runtimeHint": "uvx",
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "runtimeArguments": [
        {
          "name": "--from",
          "type": "named",
          "value": "umbra-py[mcp]",
          "description": "The server ships inside the umbra-py distribution and needs its [mcp] extra, so the package uvx installs is not the bare identifier."
        },
        {
          "type": "positional",
          "value": "umbra-mcp",
          "valueHint": "console_script",
          "description": "The console script to run from that distribution ([project.scripts] in pyproject.toml)."
        }
      ],
      "environmentVariables": [
        {
          "name": "UMBRA_CANOPY_TOKEN",
          "isSecret": true,
          "description": "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."
        },
        {
          "name": "UMBRA_INDEX_DB",
          "format": "filepath",
          "description": "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."
        },
        {
          "name": "ANTHROPIC_API_KEY",
          "isSecret": true,
          "description": "Optional. With a key, describe_scene and narrate_change call a vision model on the server. Without one they return a reading kit (picture + SAR primer) so the client's own model does the reading. A public host must not set this."
        },
        {
          "name": "OPENAI_API_KEY",
          "isSecret": true,
          "description": "Alternative provider for the same two model tools, and the encoder behind find_similar_text."
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/reesehammer/umbra-py",
    "source": "github"
  },
  "description": "Search, preview, and measure Umbra open SAR from any MCP client. Umbra ships no search API."
}