Skip to main content
Glama

duescope

What does the published website-change dataset actually say? duescope is a local forwarding client for the hosted Duesvo MCP service: it answers tools/list locally from the captured tool definitions and forwards every call to the service, returning the answers exactly as the service sends them back.

All seven tools are read-only queries over one published dataset of website changes. You can inspect its shape, search its cells, look rows up by exact key, compare rows side by side, compute summary statistics and rankings over its numeric columns, and read where the data comes from and how to cite it. There is no write, signup, or send tool in this surface.

The tools

  • dataset_columns — The columns of the dataset, which of them are numeric, the row count and the provenance banner. Call this first to learn the schema. No parameters.

  • dataset_search — Rows whose cells contain the query text (case-insensitive), up to 50; limit caps the count between 1 and 50. query is required.

  • dataset_row — The rows where a column equals a value exactly (case-insensitive). Both are required.

  • dataset_compare — The rows whose column is any of the given values (2 to 10 of them), in the order given — for "X vs Y" questions. Both are required.

  • dataset_stats — Count, min, max, mean, median and sum of a numeric column; grouping commas and currency are handled, and non-numeric rows are excluded and counted. column is required.

  • dataset_top — The highest rows by a numeric column, or the lowest when ascending is true; limit caps the count between 1 and 50. column is required.

  • dataset_provenance — The source of the data, the date it was computed, the licence and the citation. Read this to attribute a figure correctly. No parameters.

Related MCP server: llclens

Install and run

As an MCP server via npm:

npx -y @reneturcios/duescope mcp

MCP client configuration:

{
  "mcpServers": {
    "duescope": {
      "command": "npx",
      "args": ["-y", "@reneturcios/duescope", "mcp"]
    }
  }
}

As a container:

docker run -i ghcr.io/cloudcorprecords/duescope
docker run --rm ghcr.io/cloudcorprecords/duescope dataset_search '{"query":"example"}'

CLI

One binary serves both the command line and the MCP server. Each tool is a subcommand taking a single JSON string with that tool's arguments:

duescope dataset_columns '{}'
duescope dataset_search '{"query":"pricing","limit":10}'
duescope dataset_row '{"column":"domain","value":"example.com"}'
duescope dataset_compare '{"column":"domain","values":["a.example","b.example"]}'
duescope dataset_stats '{"column":"score"}'
duescope dataset_top '{"column":"score","limit":5}'
duescope dataset_provenance '{}'
duescope --version

Exit codes: 0 when the forwarded call succeeds, 1 when the upstream result is an error, and 2 for usage problems such as an unknown subcommand or a malformed JSON argument.

Configuration

  • DUESVO_MCP_URL — Overrides the upstream endpoint. The default is the pinned hosted endpoint, https://www.duesvo.site/mcp. (The override variable is a reconstruction added by this rebuild.)

The upstream registry record declares no headers, so no authentication header is ever sent; the tool surface was captured keyless.

Upstream failures — a JSON-RPC error from the service, a non-2xx response, an unreadable body, or a request that fails outright — are reported to the caller as an error result whose text starts with duescope error:.

How forwarding works

The first forwarded call opens a session: an initialize request (protocol version 2025-03-26), followed by a notifications/initialized notification, then the tools/call itself. If the service answers the initialize request with an Mcp-Session-Id header, that value is carried on every later request, and the open session is reused for the rest of the process. Replies are accepted either as plain JSON or as server-sent events. Successful results pass through verbatim, including any isError flag and any extra fields the service includes.

Development

npm install
npm run build   # tsc -> dist/ (dist/cli.js is the bin)
npm test        # tsx --test test/*.test.ts — stubbed upstream, no network
npm run dev     # run the CLI from source

The test suite checks the served tool list against the captured surface (all 7 tools, deep-equal, in order, with titles served verbatim and no required key added to the two tools that carry none), exercises the session handshake and its reuse, verifies that no Authorization or X-API-Key header is ever sent under any environment, and verifies that arguments go upstream untouched and results come back untouched.

License

MIT — see LICENSE. Copyright (c) 2026 Rene Turcios.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables read-only querying of the hosted Limslane dataset, including schema inspection, text and exact-value search, row comparison, column statistics, ranking, and provenance retrieval without local caching or computation. It forwards queries to the hosted Limslane MCP service and returns results verbatim.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables read-only inspection and querying of the LLC Lane dataset, including schema and provenance discovery, row search and exact lookup, side-by-side comparisons, column statistics, and top or bottom rankings.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables querying a hosted read-only DrawScheduleWorks dataset through MCP tools for schema and provenance inspection, cell search, exact row lookup, value comparison, numeric statistics, and top-row ranking without downloading the dataset.
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients to query the hosted Lobbyvo dataset, including searching rows, fetching and comparing exact values, computing column statistics, ranking rows, and retrieving provenance for citation.
      MIT