Paperless MCP server
Paperless-NGX over MCP: search, read, upload and tag documents; manage correspondents and types.
1 stars96 downloads/wk
Reviews
Write oneNobody has reviewed Paperless MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Paperless MCP tools (49, 16 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
add_document_noteAppend a note to a document.
bulk_edit_correspondentsApply a bulk operation to a set of correspondents.
bulk_edit_document_typesApply a bulk operation to a set of document types.
bulk_edit_documentsApply a bulk operation to a set of documents.
bulk_edit_tagsApply a bulk operation to a set of tags.
create_correspondentwrite actionCreate a new correspondent.
create_custom_fieldwrite actionCreate a new custom field.
create_document_typewrite actionCreate a new document type.
create_tagwrite actionCreate a new tag.
delete_correspondentwrite actionDelete a correspondent.
delete_custom_fieldwrite actionDelete a custom field.
delete_documentwrite actionDelete a document.
delete_document_notewrite actionRemove a note from a document.
delete_document_typewrite actionDelete a document type.
delete_tagwrite actionDelete a tag.
get_correspondentFetch a correspondent by ID.
get_custom_fieldFetch a custom field by ID.
get_documentFetch one document by ID.
get_document_contentReturn the OCR'd text content of a document.
get_document_historyReturn the audit history for a document.
get_document_metadataReturn technical metadata for a document (checksums, filenames, etc.).
get_document_notesReturn notes attached to a document.
get_document_suggestionsReturn Paperless's classifier suggestions for a document.
get_document_thumbnailReturn the document's thumbnail as inline image content.
get_document_typeFetch a document type by ID.
get_remote_versionCheck whether a newer release of Paperless-NGX exists upstream.
get_saved_viewFetch a saved view by ID.
get_share_linkFetch a share link by ID.
get_statisticsFetch collection-level statistics.
get_storage_pathFetch a storage path by ID.
get_tagFetch a tag by ID.
get_taskFetch a task by UUID. Returns ``None`` if no such task exists.
list_correspondentsList correspondents.
list_custom_fieldsList custom fields.
list_document_typesList document types.
list_documentsList documents with optional filters. Returns one page.
list_saved_viewsList saved views.
list_share_linksList share links (optionally filtered by document).
list_storage_pathsList storage paths.
list_tagsList tags.
list_tasksList Paperless Celery tasks.
search_documentsFull-text search documents.
update_correspondentwrite actionPatch selected fields on a correspondent.
update_custom_fieldwrite actionPatch selected fields on a custom field definition.
update_documentwrite actionPatch selected fields on a document.
update_document_typewrite actionPatch selected fields on a document type.
update_tagwrite actionPatch selected fields on a tag.
upload_documentwrite actionUpload a document. Returns the task UUID for polling via `get_task`.
wait_for_taskPoll until the task reaches a terminal state or times out.
Public scan report
scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it
- Code scan79 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 2 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Paperless MCP compares
Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 83/100
- higher than 70% of 3,470 Web search servers
- Tools
- 49
- the typical Web search server has 5
- Tools that change things
- 33%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 55% of 1,786 Web search servers
- Downloads a week
- 96
- more than 56% of 827 Web search servers with a package
What its tools let an agent do: 32 read · 6 create · 5 change · 6 delete
Release history: 3 versions in the registry since 2026-09-17, latest 2026-09-21, typically one every 3 days.
Install Paperless MCP in Claude Code, Cursor or VS Code
claude mcp add paperless-mcp -- uvx pvliesdonk-paperless-mcp
What the publisher says
From the Paperless MCP repository's README, as published. We do not edit it. Read it on GitHub
<!-- DOMAIN-START --> <!-- Add an optional project logo or project-specific header here. Kept across copier update. --> <!-- DOMAIN-END -->
Paperless MCP
<!-- mcp-name: io.github.pvliesdonk/paperless-mcp -->
Paperless-NGX over MCP: search, read, upload and tag documents; manage correspondents and types.
Documentation | Config wizard | PyPI | Docker
Features
<!-- DOMAIN-START -->
<!-- DOMAIN-END -->
- File transfer links: Download document files and full OCR Markdown over HTTP. Upload files, including Markdown, through the same transfer route. Set PAPERLESSMCPBASE_URL to enable the tools. File bytes stay outside model context. See file transfer links.
- Document search & retrieval: full-text and filtered list queries against Paperless-NGX, plus access to extracted OCR text, metadata, and thumbnails.
- Tag, correspondent, document-type, custom-field management: full CRUD and bulk-edit for every classification dimension Paperless exposes.
- Document lifecycle supports uploads, field changes, notes, audit history, and AI-suggested tags/correspondents/types.
- Operational introspection covers saved views, storage paths, share links, background tasks (with waitfortask), statistics, and an upstream release check for Paperless-NGX.
- MCP tools: 49 LLM-visible tools with Lucide icons; see src/paperless_mcp/tools/.
- MCP resources: 16 URIs exposing bounded document previews and domain collections; see src/paperless_mcp/resources/.
What you can do with it
<!-- DOMAIN-START --> With this server mounted in an MCP client (Claude, etc.), you can:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Paperless MCP: common questions
- Is Paperless MCP server safe?
- Mostly: it is graded B (83/100). Read the Paperless MCP safety report
- How do I install Paperless MCP?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Paperless MCP need an API key?
- Yes. The registry entry asks for
PAPERLESS_MCP_API_TOKEN,PAPERLESS_MCP_BEARER_TOKEN,PAPERLESS_MCP_OIDC_CLIENT_SECRET,PAPERLESS_MCP_OIDC_JWT_SIGNING_KEY. - Is Paperless MCP maintained?
- The last commit was 22 days ago (2026-10-13). The latest release is v3.0.0.
- What can I use instead of Paperless MCP?
- Servers from other publishers that do the same job: Free Search MCP server, reMarkable MCP Server and CLIO Web MCP server.
- How does Paperless MCP compare with other Web search MCP servers?
- safety score 83/100 (higher than 70% of 3,470 Web search servers); tools 49 (the typical Web search server has 5); tools that change things 33% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Paperless MCP
Same job from other publishers: the closest match first, then the best rated.
Free SearchNo-API-key web search, page fetching and document reading across many engines. Local-first.not reviewedEstablishedB- reMarkable MCP ServerRead, render, search, and manage reMarkable documents through MCPnot reviewedEstablishedB
- CLIO WebProvider-fixed web search plus transparent URL, DOI, and document fetchingnot reviewedEstablishedA
- Vadivam IconsSearch 24px outline icons by name, tag, or category and get SVG or framework code.not reviewedEstablishedA
- Ref ToolsToken-efficient search for coding agents over public and private documentation.not reviewedEstablishedA