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.1-
- AlicenseCqualityBmaintenanceEnables searching, tagging, uploading, and reading documents in Paperless-NGX, with management of tags, correspondents, document types, and custom fields via MCP tools and resources.5057 PyPI1MIT
- AlicenseNot gradedqualityDmaintenanceEnables managing Paperless-NGX documents, tags, correspondents, and document types via natural language. Supports document searching, downloading, uploading, and bulk editing.133 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 gradedqualityDmaintenanceMCP server for Paperless-ngx document management, enabling search, OCR content access, metadata updates, tag/correspondent/type management, and duplicate detection via natural language.1-
TDQS
Scored across 45 tools
Most tools map to a distinct resource+action, and the descriptions do a good job steering callers (e.g. list_documents vs query_documents vs search_passages). The main fuzziness is the document-search cluster: list_documents, query_documents, search_documents (deprecated compatibility wrapper), and search_passages all retrieve documents, so an agent must read descriptions carefully to pick the right one. Deprecating search_documents mitigates this, but the overlap keeps it below full clarity.
Nearly everything follows a predictable verb_noun pattern (list_tags, create_tag, update_tag, delete_tag, get_correspondent, etc.) across all resource families. Minor deviations exist: post_document instead of create_document, and bulk_edit_* as a separate prefix rather than part of the standard verb set. These are readable and consistent enough not to confuse.
45 tools is heavy, but the domain genuinely spans seven resource types (documents, notes, tags, correspondents, document types, custom fields, mail accounts/rules) each with CRUD, so much of the surface earns its place. Still, the count is inflated by a deprecated wrapper and a near-identical bulk_edit_* variant for every entity, pushing it into borderline territory.
Coverage is broad: documents have create/read/update/delete (delete via bulk_edit_documents), content paging, download/thumbnail, and search; tags, correspondents, document types, and custom fields all have full CRUD plus bulk. Gaps are minor: no single delete_document (only bulk method), no get_tag (list only), and mail accounts are read/process-only with no create/update/delete, though those may be intentional.