Skip to main content
Glama
cubinet-code

paperless-ngx-mcp

by cubinet-code
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to paperless-ngx-mcp

No user-submitted related servers found.

    Related Servers

    • Paperless-NGX MCP Server

      MephistoJB
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables managing Paperless-NGX documents, tags, correspondents, and document types via natural language. Supports document searching, downloading, uploading, and bulk editing.
      79 npm
      ISC

    • paperless-ngx-mcp

      cbsmiley
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables Claude AI to interact with Paperless-NGX document management through natural language, offering 50 tools for full CRUD operations and management.
      383 npm
      MIT

    • Paperless MCP

      pvliesdonk
      A
      license
      C
      quality
      A
      maintenance
      Enables searching, tagging, uploading, and reading documents in Paperless-NGX, with management of tags, correspondents, document types, and custom fields via MCP tools and resources.
      50
      80 PyPI
      1
      MIT

    • paperless-mcp

      tiziano5
      A
      license
      Not graded
      quality
      D
      maintenance
      Connects Claude to a self-hosted Paperless-ngx document archive, enabling natural language search, retrieval, and taxonomy browsing of documents.
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.4/5.0

    Scored across 109 tools

    Disambiguation3/5

    Most tools target distinct resource+action pairs and the descriptions go out of their way to disambiguate (e.g. bulk object edits vs. document edits, classifier vs. AI suggestions). However, with 109 tools there are large overlapping clusters that will still confuse selection: four task tools (list_tasks, list_active_tasks, get_task_status_counts, get_task_summary), three share-link listers, three document-version mutators, and multiple search/filter entry points (search_documents vs list_documents search vs search_autocomplete). The density of near-boundary tools keeps this from being high.

    Naming Consistency4/5

    Overwhelmingly a verb_noun convention: list_/get_/create_/update_/delete_ across every resource, plus uniform patterns like edit_*_bulk and test_*/process_* for mail. Minor deviations (post_document instead of create_document, download_document/bulk, upload_document_version, get_next_asn) are readable but break strict predictability.

    Tool Count1/5

    109 tools is far beyond any reasonable scope for a single server and lands in the extreme-mismatch band. Even with a broad domain (documents plus all metadata objects, workflows, mail, sharing, tasks), the surface is massively bloated and should be consolidated or split into sub-servers.

    Completeness5/5

    The surface covers the full Paperless-NGX lifecycle: documents (create/read/update/delete/trash/restore/versions/notes/history/preview/download/email), all metadata objects with CRUD and bulk operations, workflows with triggers/actions, mail accounts and rules, share links and bundles, tasks, saved views, statistics and system status. There are no obvious dead ends for the stated domain.

    Maintenance

    ActivityMaintained
    ResponsivenessUnresponsive

    Resources