"Cargo Doc" matching MCP servers:

Agent-native Amazon review intelligence — fetches verified reviews from 10 marketplaces via real Shulex OpenAPI (not scrapers) and produces copy-ready listing improvements grounded in actual customer language. Backed by a 2B-review historical dataset that Helium 10 / Jungle Scout can't replicate. Works in any MCP client (Claude Code, Claude Desktop, ChatGPT, Cursor, Windsurf, VS Code, Cline).

Enables clients to create, query and edit QGIS projects and vector data in an isolated, new headless PyQGIS process, exporting GeoJSON/GeoPackage, saving and reopening editable QGZ bundles, and rendering PNG maps through typed MCP tools. All operations are workspace-relative with strict path and geometry validation, and never attach to or modify a running QGIS desktop session.

Enables AI agents to drive a persistent, isolated ParaView session for scientific visualization: creating and editing spheres, clipping with planes, importing single-file VTI/VTP/VTU datasets, extracting contours, exporting verified datasets, saving native PVSM states, and rendering display-backed PNG previews. All operations are confined to a single operator-owned workspace on a Linux-only, display-backed host, with no attachment to existing GUI pipelines.

Enables answering business questions over local SQL Server WideWorldImporters data through MCP, with support for both STDIO and Streamable HTTP endpoints.