Paperless-NGX MCP Server
Related Servers
Alternatives to Paperless-NGX MCP Server
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceEnables interaction with a paperless-ngx document management system through MCP tools, allowing document search, retrieval, upload, and metadata management via natural language.-
- AlicenseCqualityAmaintenanceEnables searching, tagging, uploading, and reading documents in Paperless-NGX, with management of tags, correspondents, document types, and custom fields via MCP tools and resources.5087 PyPI1MIT
- AlicenseNot gradedqualityDmaintenanceEnables managing Paperless-NGX documents, tags, correspondents, and document types via natural language. Supports document searching, downloading, uploading, and bulk editing.78 npmISC
- 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-
- AlicenseAqualityCmaintenanceEnables AI assistants to search, inspect OCR content, download, upload, and manage documents in a Paperless-ngx archive through natural language.91MIT
- 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.-
TDQS
Scored across 45 tools
Most tools target a distinct resource+action, and descriptions clearly delineate overlapping areas (query_documents vs search_passages vs list_documents). The lingering deprecated search_documents alongside three other document-retrieval tools introduces some confusion, and bulk_edit_* tools partially overlap with individual delete_* operations, but boundaries are mostly clear.
The set follows a strong verb_noun convention (list_, get_, create_, update_, delete_, bulk_edit_, search_, query_). Minor deviations exist: post_document instead of create_document/upload_document, and process_mail_account vs the mail-rule verbs, but these are readable and few.
At 45 tools this surface is heavy. While each does roughly map to a resource/action across documents, tags, correspondents, document types, custom fields, notes, and mail accounts/rules, the sheer number (with deprecated and bulk variants layered on top) exceeds what most agents can select from reliably.
Coverage is broad: full CRUD for correspondents, document types, tags, custom fields, and mail rules, plus rich document read/upload/query/notes operations. Minor gaps remain — no singular get_tag and no first-class delete_document (only via bulk_edit_documents) — but agents can work around these.