paperless-mcp
Related Servers
Alternatives to paperless-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceA read-only and write MCP server for Paperless-ngx, enabling document listing, metadata retrieval, and creation of tags, correspondents, document types, and sorting workflows via natural language.MIT
- FlicenseNot gradedqualityCmaintenanceMCP server for Paperless-ngx document management, enabling search, OCR content access, metadata updates, tag/correspondent/type management, and duplicate detection via natural language.-
- FlicenseAqualityCmaintenanceMCP server for Paperless-ngx document management. Enables AI models to search, retrieve, update documents and manage metadata.7-
- AlicenseAqualityBmaintenanceAn MCP server that puts a paperless-ngx document archive within reach of AI assistants, enabling full-text search, reading, filing, uploading, and managing documents and taxonomy through the paperless-ngx REST API.1611 npmMIT
- AlicenseAqualityAmaintenanceA Model Context Protocol server for Paperless-ngx that provides full REST API coverage for document management, including search, upload, metadata, workflows, sharing, and admin, with token-frugal responses and a scoped toolset.8555 npm1MIT
- FlicenseAqualityBmaintenanceA privacy-first MCP server for Paperless-ngx that lets an LLM agent search, organize, tag, and reference documents without exposing full text unless explicitly requested.13-
TDQS
Scored across 44 tools
Most tools target a distinct resource+action, and descriptions clearly differentiate get_document (metadata) vs get_document_content vs get_document_thumbnail vs download_document. However, the document-listing trio (list_documents, query_documents, and the deprecated search_documents) overlaps, forcing the agent to reason about which to pick even though the descriptions do explain the boundary.
The set follows a strong verb_noun convention (list_/get_/create_/update_/delete_/bulk_edit_ + resource) applied uniformly across tags, correspondents, document types, and custom fields. The only notable deviation is post_document (instead of create_document), a minor inconsistency in an otherwise predictable scheme.
At 44 tools this is heavy, well above the typical 3-15 sweet spot, though the breadth is partly justified by six distinct resource domains (documents, tags, correspondents, document types, custom fields, mail). Repetition such as five near-identical bulk_edit_* tools and the deprecated search_documents adds weight without fully earning its place.
The surface is comprehensive: full CRUD plus bulk operations across all major entities, document content/thumbnail/download, notes, and mail accounts/rules. Minor gaps remain—storage paths are referenced as filters but have no management tools, and single-document deletion is only reachable through bulk_edit_documents' 'delete' method.