INDIVIDUAL MCP TOOL

search_records

Search the archive with filters for collection, entity, content type, island and year.

usvipublicrecords.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://mcp.usvipublicrecords.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for search_records and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.usvi-public-records]
url = "https://mcp.usvipublicrecords.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "usvi-public-records": {
      "type": "http",
      "url": "https://mcp.usvipublicrecords.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: usvi-public-records
Remote MCP URL: https://mcp.usvipublicrecords.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "usvi-public-records": {
      "url": "https://mcp.usvipublicrecords.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "usvi-public-records": {
      "type": "http",
      "url": "https://mcp.usvipublicrecords.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "usvi-public-records",
  "transport": "streamable-http",
  "url": "https://mcp.usvipublicrecords.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

search — Find U.
fetch — Retrieve one document by archive id: its catalogue record and up to the first 40,000 characters of its extracted text, with next_offset when more remains.
get_document — The full catalogue record for one document: collection, entity, dates, page count, SHA-256, extraction status and the URL of the original at its source.
get_document_text — The extracted text of one document, in windows of up to 40,000 characters (default 20,000).
list_collections — The collections in this server, with document counts.
archive_stats — Reports how many documents this server can search, how much text that covers, how much of the archive each search filter can see, and whether the index matches the published archive.