MCP server for Paperless-ngx 3.x — full REST API coverage, schema-aware, token-frugal.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
PAPERLESS_TOKENAPI keyrequiredPaperless-ngx API token
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
list_usersUsers on this instance with their IDs and permissions. You need these IDs to set documentUsers on this instance with their IDs and permissions. You need these IDs to set document
No input schema was published for this tool.
list_groupsPermission groups with their IDs and member counts, for use in set_permissions payloads.Permission groups with their IDs and member counts, for use in set_permissions payloads.
No input schema was published for this tool.
get_profileThe profile of the user whose API token this server is using. Confirms which account you areThe profile of the user whose API token this server is using. Confirms which account you are
No input schema was published for this tool.
get_configurationThe instance's application configuration: OCR defaults, output type, barcode settings, AIThe instance's application configuration: OCR defaults, output type, barcode settings, AI
No input schema was published for this tool.
list_logsNames of the log files available, e.g. 'paperless' and 'mail'.Names of the log files available, e.g. 'paperless' and 'mail'.
No input schema was published for this tool.
get_logRead one of the instance's log files. Returns the tail by default — logs are long and mostlyRead one of the instance's log files. Returns the tail by default — logs are long and mostly
No input schema was published for this tool.
get_userOne user record by ID, including group membership and permission flags. Use it to resolve an owner ID
to a human name.One user record by ID, including group membership and permission flags. Use it to resolve an owner ID to a human name.
No input schema was published for this tool.
bulk_edit_documentsprivilegedApply one operation to many documents at once. Far cheaper than looping update_document, and theApply one operation to many documents at once. Far cheaper than looping update_document, and the
No input schema was published for this tool.
merge_documentsMerge several documents into one new PDF, in the order given. The originals stay unlessMerge several documents into one new PDF, in the order given. The originals stay unless
No input schema was published for this tool.
rotate_documentsRotate every page of the given documents clockwise by 90, 180 or 270 degrees.Rotate every page of the given documents clockwise by 90, 180 or 270 degrees.
No input schema was published for this tool.
edit_pdfprivilegedReorder, rotate, remove or split out pages of a single document, producing a new document.Reorder, rotate, remove or split out pages of a single document, producing a new document.
No input schema was published for this tool.
remove_pdf_passwordprivilegedDecrypt password-protected PDFs so Paperless can OCR them. The password is sent to your PaperlessDecrypt password-protected PDFs so Paperless can OCR them. The password is sent to your Paperless
No input schema was published for this tool.
reprocess_documentsRe-run OCR and the archive generation for the given documents, e.g. after changing OCR settings.Re-run OCR and the archive generation for the given documents, e.g. after changing OCR settings.
No input schema was published for this tool.
delete_documentsprivilegedMove several documents to the trash at once. Recoverable until the trash is emptied.Move several documents to the trash at once. Recoverable until the trash is emptied.
No input schema was published for this tool.
list_custom_fieldsCustom fields defined on this instance, with their IDs, data types and how many documents useCustom fields defined on this instance, with their IDs, data types and how many documents use
No input schema was published for this tool.
get_custom_fieldOne custom field definition including its select options, if any.One custom field definition including its select options, if any.
No input schema was published for this tool.
create_custom_fieldDefine a new custom field. The data type cannot be changed afterwards, so pick it deliberately.Define a new custom field. The data type cannot be changed afterwards, so pick it deliberately.
No input schema was published for this tool.
update_custom_fieldRename a custom field or adjust its extra_data (e.g. add select options).Rename a custom field or adjust its extra_data (e.g. add select options).
No input schema was published for this tool.
delete_custom_fieldprivilegedDelete a custom field definition and every value stored in it, across all documents.Delete a custom field definition and every value stored in it, across all documents.
No input schema was published for this tool.
search_documentsFind documents by full-text search, metadata filters, or both. This is the main entry point forFind documents by full-text search, metadata filters, or both. This is the main entry point for
No input schema was published for this tool.
get_documentFetch one document's metadata by ID: title, correspondent, type, tags, dates, custom fields, notesFetch one document's metadata by ID: title, correspondent, type, tags, dates, custom fields, notes
No input schema was published for this tool.
get_document_contentReturn the OCR/extracted text of one document. Deliberately a separate tool: this is the mostReturn the OCR/extracted text of one document. Deliberately a separate tool: this is the most
No input schema was published for this tool.
update_documentChange metadata on a single document. Only the fields you pass are modified.Change metadata on a single document. Only the fields you pass are modified.
No input schema was published for this tool.
delete_documentprivilegedMove a document to the trash. It stays recoverable until the trash is emptied or the retentionMove a document to the trash. It stays recoverable until the trash is emptied or the retention
No input schema was published for this tool.
get_document_metadataTechnical file metadata for a document: checksums, byte sizes, MIME type, stored filename, whetherTechnical file metadata for a document: checksums, byte sizes, MIME type, stored filename, whether
No input schema was published for this tool.
get_document_historyAudit trail of changes to a document — who changed which field, and when. Requires audit loggingAudit trail of changes to a document — who changed which field, and when. Requires audit logging
No input schema was published for this tool.
get_document_suggestionsPaperless' own suggestions for a document — correspondents, tags, document types and dates itsPaperless' own suggestions for a document — correspondents, tags, document types and dates its
No input schema was published for this tool.
get_document_ai_suggestionsSuggestions from the instance's configured LLM backend (Paperless-ngx 3.x, only if AI features areSuggestions from the instance's configured LLM backend (Paperless-ngx 3.x, only if AI features are
No input schema was published for this tool.
get_next_asnThe next free archive serial number, for filing a physical document alongside its scan.The next free archive serial number, for filing a physical document alongside its scan.
No input schema was published for this tool.
get_selection_dataFor a set of document IDs, return how many of them carry each tag, correspondent, document type andFor a set of document IDs, return how many of them carry each tag, correspondent, document type and
No input schema was published for this tool.
download_documentSave a document's file to disk on the machine running this MCP server and return the path.Save a document's file to disk on the machine running this MCP server and return the path.
No input schema was published for this tool.
get_document_thumbnailReturn the document's thumbnail image inline so it can actually be looked at.Return the document's thumbnail image inline so it can actually be looked at.
No input schema was published for this tool.
bulk_download_documentsDownload several documents as one zip archive, written to the download directory.Download several documents as one zip archive, written to the download directory.
No input schema was published for this tool.
upload_documentprivilegedHand a file to Paperless for consumption. Provide either `path` (a file on the machine runningHand a file to Paperless for consumption. Provide either `path` (a file on the machine running
No input schema was published for this tool.
email_documentsSend one or more documents by email from the Paperless instance. This sends real mail to realSend one or more documents by email from the Paperless instance. This sends real mail to real
No input schema was published for this tool.
list_document_notesNotes attached to a document, with authors and timestamps. Notes hold context the OCR text doesNotes attached to a document, with authors and timestamps. Notes hold context the OCR text does
No input schema was published for this tool.
create_document_noteAttach a free-text note to a document. Use this to record context that belongs with the document
rather than in the conversation — why it was kept, what was agreed, what to do next.Attach a free-text note to a document. Use this to record context that belongs with the document rather than in the conversation — why it was kept, what was agreed, what to do next.
No input schema was published for this tool.
delete_document_noteprivilegedRemove a note from a document. Not recoverable.Remove a note from a document. Not recoverable.
No input schema was published for this tool.
list_mail_accountsIMAP accounts Paperless fetches documents from. Passwords are not returned.IMAP accounts Paperless fetches documents from. Passwords are not returned.
No input schema was published for this tool.
get_mail_accountOne mail account in full: server, port, username, folder and security settings. Passwords are never
returned by the API.One mail account in full: server, port, username, folder and security settings. Passwords are never returned by the API.
No input schema was published for this tool.
40 of 40 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
MCP server for Paperless-ngx 3.x — full REST API coverage, schema-aware, token-frugal.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the depth-4 limit. Anything below that level was never resolved.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
53 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+41 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.