MCP server for terminal commands, file operations, and process management
Nothing to run from here
Paperless-ngx is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
127
downloads a day
local
runs on your machine
2k
downloads in 30d
What it does
Full Paperless-ngx API for AI assistants: search, tag, edit and upload documents, workflows and more
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'PAPERLESS_URL=${PAPERLESS_URL}' --env 'PAPERLESS_API_KEY=${PAPERLESS_API_KEY}' --transport stdio cubinet-code-paperless-ngx-mcp '--' npx -y paperless-ngx-mcp
# 2 — ask your agent for something these tools do
# edit_documents_bulk, post_document, list_documents and 103 more
It needs PAPERLESS_URL, PAPERLESS_API_KEY: this reads them from your environment, so export them first.
Paperless-ngx costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CCAll 1 server
cubinet-code1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Paperless-ngx as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads PAPERLESS_URL (Base URL of your Paperless-ngx instance, e.g. https://paperless.example.com), PAPERLESS_API_KEY (Paperless-ngx API token (My Profile → generate token)) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx PAPERLESS_URL …, setx PAPERLESS_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'PAPERLESS_URL=${PAPERLESS_URL}' --env 'PAPERLESS_API_KEY=${PAPERLESS_API_KEY}' --transport stdio cubinet-code-paperless-ngx-mcp '--' npx -y paperless-ngx-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: PAPERLESS_URL — Base URL of your Paperless-ngx instance, e.g. https://paperless.example.com; PAPERLESS_API_KEY — Paperless-ngx API token (My Profile → generate token). You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
106 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
No parameter schema on file.
No parameter schema on file.
List and filter documents by fields such as title, correspondent, document type, tag, storage path, creation date, and more. IMPORTANT: For queries like
No parameter schema on file.
Get a specific document by ID with full details including correspondent, document type, tags, and custom fields. Note: Document content is excluded from results by default. Use
No parameter schema on file.
Get the text content of a specific document by ID. Use this when you need to read or analyze the actual document text.
No parameter schema on file.
Full text search for documents. This tool is for searching document content, title, and metadata using a full text query. For general document listing or filtering by fields, use
No parameter schema on file.
Download a document file by ID. Returns the document as a base64-encoded resource.
No parameter schema on file.
Get a document thumbnail (image preview) by ID. Returns the thumbnail as a base64-encoded WebP image resource.
No parameter schema on file.
No parameter schema on file.
Send a document via email to one or more recipients.
No parameter schema on file.
Get the change history / audit log for a document, showing who changed what and when.
No parameter schema on file.
Get a full-page preview image of a document. Returns the preview as a base64-encoded image resource.
No parameter schema on file.
List all workflow actions with optional pagination.
No parameter schema on file.
Get a specific workflow action by ID.
No parameter schema on file.
No parameter schema on file.
Update fields on ONE workflow action (PATCH — only fields you supply are changed). Use get_workflow_action first to see its current shape. To change the actions of a whole workflow, see update_workflow.
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a workflow action.
No parameter schema on file.
List all workflow triggers with optional pagination.
No parameter schema on file.
Get a specific workflow trigger by ID.
No parameter schema on file.
No parameter schema on file.
Update fields on ONE workflow trigger (PATCH — only fields you supply are changed). Use get_workflow_trigger first to see its current shape.
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a workflow trigger.
No parameter schema on file.
List workflows (each with its nested triggers and actions) with optional pagination.
No parameter schema on file.
Get one workflow by ID, including its full triggers and actions.
No parameter schema on file.
No parameter schema on file.
Update ONE workflow (PATCH). name/order/enabled change only when passed. ⚠️
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a workflow. Documents it already processed are not changed.
No parameter schema on file.
List all correspondents with optional filtering and pagination. Correspondents represent entities that send or receive documents.
No parameter schema on file.
Get a specific correspondent by ID with full details including matching rules.
No parameter schema on file.
Create a new correspondent with optional matching pattern and algorithm for automatic document assignment.
No parameter schema on file.
Update fields on ONE correspondent (PATCH — only fields you supply are changed). Editable fields: name, match (matching pattern), matching_algorithm, is_insensitive. To assign this correspondent to documents, use edit_documents_bulk with method
No parameter schema on file.
Manage correspondent objects themselves (permissions, delete). ⚠️ This does NOT assign correspondents to documents — use edit_documents_bulk with method
No parameter schema on file.
No parameter schema on file.
Get a specific custom field by ID with full details including data type and extra configuration.
No parameter schema on file.
Create a new custom field with a specified data type (string, url, date, boolean, integer, float, monetary, documentlink, or select). For monetary fields, values must use currency code prefix format (e.g., USD10.00, GBP123.45) — NOT trailing symbol format (e.g., 10.00$).
No parameter schema on file.
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a custom field from the entire system. This will remove the field from ALL documents that use it.
No parameter schema on file.
Manage custom field definitions themselves (permissions, delete). ⚠️ This does NOT modify custom field values on documents — use edit_documents_bulk with method
No parameter schema on file.
No parameter schema on file.
Get a specific document type by ID with full details including matching rules.
No parameter schema on file.
Create a new document type with optional matching pattern and algorithm for automatic document classification.
No parameter schema on file.
Update fields on ONE document type (PATCH — only fields you supply are changed). Editable fields: name, match (matching pattern), matching_algorithm, is_insensitive. To assign this document type to documents, use edit_documents_bulk with method
No parameter schema on file.
Manage document type objects themselves (permissions, delete). ⚠️ This does NOT assign document types to documents — use edit_documents_bulk with method
No parameter schema on file.
Add a new file version to an EXISTING document instead of creating a new document — e.g. a corrected scan, a signed copy, or an unlocked PDF. The new file becomes the current version: content, search and downloads follow it, and earlier versions stay listed in the document
No parameter schema on file.
Rename a version of a document (change its version_label). Version IDs are listed in get_document
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete one non-root version of a document. The root (original) version can
No parameter schema on file.
⚠️ Fold other documents into one document as its versions: each document in merge_documents stops existing as a separate document and becomes a version of root_document_id. Use it when the same paper arrived twice (e.g. a scan and a later emailed copy). Runs asynchronously.
No parameter schema on file.
List the IMAP accounts Paperless fetches mail from. Passwords are always masked.
No parameter schema on file.
Get one mail account by ID (password masked).
No parameter schema on file.
Create an IMAP account for Paperless to fetch mail from. Nothing is fetched until a mail rule uses the account (create_mail_rule). Check the connection first with test_mail_account.
No parameter schema on file.
Update fields on ONE mail account (PATCH — only fields you supply are changed). Omit password to keep the stored one.
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a mail account and stop fetching from it. Mail rules using it are deleted too. Already-imported documents are not affected.
No parameter schema on file.
Test IMAP connection settings without saving them. Pass the full account fields. To test a SAVED account, pass its
No parameter schema on file.
Fetch mail for one account now and run its rules, instead of waiting for the schedule. Runs in the background; see list_tasks with task_type mail_fetch.
No parameter schema on file.
List mail rules: which mails Paperless imports from which account, and how it assigns title, tags, correspondent and document type.
No parameter schema on file.
Get one mail rule by ID.
No parameter schema on file.
Create a mail rule on a mail account: which folder and mails to consider, which attachments to import, and what to assign to the resulting documents.
No parameter schema on file.
Update fields on ONE mail rule (PATCH — only fields you supply are changed). E.g. switch assign_correspondent_from to 4 to stop creating a correspondent per sender.
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a mail rule. Already-imported documents are not affected.
No parameter schema on file.
List all saved views with optional pagination. Saved views store filter/sort configurations for quick access.
No parameter schema on file.
Get a specific saved view by ID with full details including filter rules.
No parameter schema on file.
Create a new saved view with filter rules and sort configuration.
No parameter schema on file.
Update fields on ONE saved view (PATCH — only fields you supply are changed). Editable fields: name, show_on_dashboard, show_in_sidebar, sort_field, sort_reverse, filter_rules. Supplying filter_rules replaces the entire rule array (not a merge).
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a saved view.
No parameter schema on file.
List all share links with optional filtering by creation date, expiration date, and pagination.
No parameter schema on file.
Get a specific share link by ID with full details.
No parameter schema on file.
Create a share link for a document. Optionally set an expiration date and file version (archive or original). Share links can
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a share link. The shared URL will stop working.
No parameter schema on file.
List all share links for a specific document.
No parameter schema on file.
List share link bundles (one public link to a ZIP of several documents) with optional status filter and pagination.
No parameter schema on file.
Get one share link bundle, including its build status (pending → processing → ready or failed), size and last_error.
No parameter schema on file.
Create ONE public share link for a ZIP of several documents. The ZIP is built in the background: the bundle starts as status
No parameter schema on file.
Re-queue a share link bundle
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a share link bundle. Its public link stops working; the documents are not affected.
No parameter schema on file.
List all storage paths with optional filtering and pagination. Storage paths define where documents are stored on disk.
No parameter schema on file.
Get a specific storage path by ID with full details including matching rules.
No parameter schema on file.
Create a new storage path with a name, path template, and optional matching rules.
No parameter schema on file.
Update fields on ONE storage path (PATCH — only fields you supply are changed). Editable fields: name, path (path template), match (matching pattern), matching_algorithm, is_insensitive. To assign this storage path to documents, use edit_documents_bulk with method
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete a storage path from the entire system. This will affect ALL documents that use this storage path.
No parameter schema on file.
Test a storage path template to see how it would resolve for documents. Useful for validating path templates before creating or updating storage paths.
No parameter schema on file.
Get system statistics including document counts, inbox status, file type breakdown, and storage information.
No parameter schema on file.
Get Paperless server status: the Paperless-ngx version (pngx_version), install type, storage, and the health of the database, search index, classifier, task queue and last sanity check. Use this to find out which Paperless version you are talking to.
No parameter schema on file.
Get classifier-based suggestions for a document
No parameter schema on file.
Get LLM-based suggestions for a document: a title, existing correspondents/tags/document types/storage paths (IDs), and suggested_* NAMES for objects that don
No parameter schema on file.
Get file metadata for a document including checksums, file sizes, and archival information.
No parameter schema on file.
List all notes for a specific document.
No parameter schema on file.
Append a user-facing note (comment/annotation) to a document. Notes are separate from the document
No parameter schema on file.
⚠️ DESTRUCTIVE: Delete a note from a document.
No parameter schema on file.
Move a document to trash (soft-delete). The document remains recoverable until the trash is emptied or the retention window expires (~30 days). Use empty_trash for permanent deletion.
No parameter schema on file.
List documents in the trash (soft-deleted documents). Document content is left out, as in list_documents.
No parameter schema on file.
Restore documents from the trash back to the system.
No parameter schema on file.
⚠️ DESTRUCTIVE: Permanently delete documents from the trash, or empty the entire trash. This action is irreversible.
No parameter schema on file.
Get search term autocomplete suggestions based on the document index.
No parameter schema on file.
Get the next available Archive Serial Number (ASN) for document filing.
No parameter schema on file.
List background tasks with their status, type, trigger source and results. Useful for monitoring document consumption and other async operations. Use the filters to narrow the list;
No parameter schema on file.
Acknowledge/dismiss completed tasks to clear them from the task list.
No parameter schema on file.
List tasks that are pending or running right now (at most 50). For finished tasks use list_tasks.
No parameter schema on file.
Get task counts: all, needs_attention (failed and unacknowledged), in_progress, completed.
No parameter schema on file.
Get per-task-type statistics over the last N days: totals, pending/success/failure counts, average duration and wait time, and last run/success/failure times.
No parameter schema on file.
Download multiple documents as a ZIP archive. Returns base64-encoded ZIP file.
No parameter schema on file.
No parameter schema on file.
Get a specific tag by ID with full details including matching rules.
No parameter schema on file.
Create a new tag with optional color, matching pattern, and matching algorithm for automatic document tagging.
No parameter schema on file.
Update fields on ONE tag (PATCH — only fields you supply are changed). Editable fields: name, color, match (matching pattern), matching_algorithm, is_insensitive, parent (parent tag ID for hierarchy). To add or remove this tag on documents, use edit_documents_bulk with method
No parameter schema on file.
Manage tag objects themselves (permissions, delete). ⚠️ This does NOT add/remove tags on documents — use edit_documents_bulk with method
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under ISC
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Paperless-ngx or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 3.2.1 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest85ca6036de018f5bf8fd78cf225027d10441e8cfd67d951b46fd0acda3d6bf50
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (106 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_correspondents | no tags | |
| get_correspondent | no tags | |
| create_correspondent | no tags | |
| update_correspondent | no tags | |
| delete_correspondent | no tags | |
| list_custom_fields | untrusted-input | untrusted-input: keyword "fetch" |
| get_custom_field | no tags | |
| create_custom_field | no tags | |
| update_custom_field | no tags | |
| delete_custom_field | no tags | |
| edit_custom_fields_bulk | no tags | |
| list_document_types | untrusted-input | untrusted-input: keyword "fetch" |
| get_document_type | no tags | |
| create_document_type | no tags | |
| update_document_type | no tags | |
| delete_document_type | no tags | |
| upload_document_version | no tags | |
| update_document_version | no tags | |
| delete_document_version | no tags | |
| merge_documents_as_versions | no tags | |
| edit_documents_bulk | no tags | |
| post_document | no tags | |
| list_documents | no tags | |
| get_document | no tags | |
| get_document_content | no tags | |
| search_documents | no tags | |
| download_document | untrusted-input | untrusted-input: keyword "download" |
| get_document_thumbnail | no tags | |
| update_document | no tags | |
| email_document | no tags | |
| get_document_history | no tags | |
| get_document_preview | no tags | |
| list_mail_accounts | no tags | |
| get_mail_account | no tags | |
| create_mail_account | untrusted-input | untrusted-input: keyword "fetch" |
| update_mail_account | no tags | |
| delete_mail_account | no tags | |
| test_mail_account | no tags | |
| process_mail_account | untrusted-input | untrusted-input: keyword "fetch" |
| list_mail_rules | no tags | |
| get_mail_rule | no tags | |
| create_mail_rule | no tags | |
| update_mail_rule | no tags | |
| delete_mail_rule | no tags | |
| list_saved_views | no tags | |
| get_saved_view | no tags | |
| create_saved_view | no tags | |
| update_saved_view | no tags | |
| delete_saved_view | no tags | |
| list_share_links | no tags | |
| get_share_link | no tags | |
| create_share_link | no tags | |
| delete_share_link | no tags | |
| list_document_share_links | no tags | |
| list_share_link_bundles | no tags | |
| get_share_link_bundle | no tags | |
| create_share_link_bundle | no tags | |
| rebuild_share_link_bundle | no tags | |
| delete_share_link_bundle | no tags | |
| list_storage_paths | no tags | |
| get_storage_path | no tags | |
| create_storage_path | no tags | |
| update_storage_path | no tags | |
| delete_storage_path | no tags | |
| test_storage_path | no tags | |
| get_statistics | no tags | |
| get_system_status | no tags | |
| get_filing_options | no tags | |
| get_document_suggestions | no tags | |
| get_document_ai_suggestions | no tags | |
| get_document_metadata | no tags | |
| list_document_notes | no tags | |
| create_document_note | no tags | |
| delete_document_note | no tags | |
| delete_document | no tags | |
| list_trash | no tags | |
| restore_from_trash | no tags | |
| empty_trash | no tags | |
| search_autocomplete | no tags | |
| get_next_asn | no tags | |
| list_tasks | no tags | |
| acknowledge_tasks | no tags | |
| list_active_tasks | no tags | |
| get_task_status_counts | no tags | |
| get_task_summary | no tags | |
| download_documents_bulk | untrusted-input | untrusted-input: keyword "download" |
| list_tags | untrusted-input | untrusted-input: keyword "fetch" |
| get_tag | no tags | |
| create_tag | no tags | |
| update_tag | no tags | |
| delete_tag | no tags | |
| list_workflow_actions | no tags | |
| get_workflow_action | no tags | |
| create_workflow_action | no tags | |
| update_workflow_action | no tags | |
| delete_workflow_action | no tags | |
| list_workflow_triggers | no tags | |
| get_workflow_trigger | no tags | |
| create_workflow_trigger | no tags | |
| update_workflow_trigger | no tags | |
| delete_workflow_trigger | no tags | |
| list_workflows | no tags | |
| get_workflow | no tags | |
| create_workflow | no tags | |
| update_workflow | no tags | |
| delete_workflow | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest85ca6036de018f5b
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 3.2.1. Pin a release below and the command asks for exactly that one.
3.2.1
30 Sep 2026
latestNo release note was published with this version.
3.2.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Paperless-ngx can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.