Derive vs Paperless Ngx
A side-by-side look at the Derive and Paperless Ngx MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Derive for developer tools work as a local process; choose Paperless Ngx for developer tools as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Derive when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
DERIVE_SERVER, DERIVE_TOKEN. - You want tools like
list_workspaces, list_artifacts, search.
Choose Paperless Ngx when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
PAPERLESS_URL, PAPERLESS_API_KEY. - You want tools like
edit_documents_bulk, post_document, list_documents.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Developer Tools | Developer Tools |
| Quality signal | 64/100 · Good | 65/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | DERIVE_SERVERDERIVE_TOKEN | PAPERLESS_URLPAPERLESS_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 30 | 11 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 8 | 109 |
| Full listing | View Derive | View Paperless Ngx |
Tools & capabilities
Derive tools 8
list_workspacesList every workspace signed in on this machine you can act in — id, name, your role, local description, and which is active. One login reaches them all; pass a workspace's id or name as the `workspace` argument to list_artifacts / read / catch_up / comment / publish to act there for that call.list_artifactsList the artifacts in your workspace — short id, title, kind, current version, access, and browse `tags`. Defaults to this session's workspace; pass `workspace` (id or name from list_workspaces) to list another. Pass `tag` to list only artifacts carrying that tag (organize shows the vocabulary). Start here to find what to work on, then catch_up or read it.searchFind text within ONE artifact, or across a WORKSPACE — same tool, same behavior as the remote MCP server's `search`. Pass short_id to grep one artifact: matching lines with line numbers (and optional context), ripgrep-style, so you can then `read` a narrow `lines` range or `edit` that spot. Omit short_id to search across the workspace — the artifacts you can see, ranked by relevance and grouped by artifact — find WHICH doc has something before opening it. Searches the exact source by default (in:'text' searches the visible text instead). The query is matched literally (metacharacters are not special).readRead an artifact's CONTENT by short id, as Markdown by default (HTML is converted). Omit `section` to see the outline first (heading slugs for a single-file doc, page paths for a bundle) — call again with a `section` (or "*" for the full document) once you know what you want. Pass `format:'html'` for the exact source (needed before publish `edits`), or a past `version` for history. Also accepts derive://guide, /connect, or /compatibility so the onboarding strings in server instructions work even when MCP resources do not. For what CHANGED or the comment threads, use catch_up instead.catch_upSTART HERE on an artifact. Its state in one call: a summary, the review round, the versions since `since_version`, the open (and outdated) comment threads, and the full version history. Pass `comments` (open / addressed / resolved / outdated) to instead get that filtered thread list — your feedback queue. Pass `response_format='detailed'` (optionally with `since_version`/`to_version`) to fold in a line diff between two versions — of their readable Markdown form, not raw HTML. WAITING ON A REVIEW? Pass `wait` (seconds, max 50) to block until the human sends back — chain these instead of sleeping between polls.commentLeave feedback, reply in a thread, react, and/or resolve or reopen a thread. Anchor a NEW comment to text with `quote`, or to a linked-bundle loop/graph part with `visual_target`. Reply by passing the thread id as `reply_to`.organizeTags and collections in one tool — the library's findability layer. • READ (no `short_ids`): the workspace's tag vocabulary (tag → count) and its collections. Call this before tagging to reuse an existing tag over a near-duplicate. • READ (with `short_ids`): those artifacts' current tags + collections, plus `suggested` tags drawn from the most semantically-similar docs (when one id is given). • WRITE: pass `add`/`remove`/`set` to change tags, `collection` to file artifacts, or `state:'archived'`/`'live'` to archive and restore. Each artifact is authorized on its own; ones you can't touch are skipped. Tag freely and reuse the vocabulary — a well-tagged library is findable. Collections are heavier: a tag for plain findability, a collection when a set is a real unit.publishPublish a single-file artifact and get a permanent URL, versions, and feedback (a chat-local artifact has none of these). OMIT short_id to create a NEW artifact (title recommended); PASS short_id to publish a new version (same URL). Provide the body as `content_path` (a local file this server reads and uploads — preferred, zero tokens) or `content` (inline text). To CHANGE PART of an existing artifact, prefer `edits` (exact-match search/replace against the stored source — read format:'html' first) over resending everything. Pass `addresses` with the thread ids this revision resolves. (Multi-page bundles are published via the web app or the remote /mcp server.) FULLY-STYLED HTML renders as-authored (own <style>/scripts/fonts) in the sandboxed viewer — declare your own <meta name="viewport"> to skip the mobile-reflow injection, and self-host binaries via POST /v1/assets (images and woff2 fonts) instead of inlining base64.
Paperless Ngx tools 109
edit_documents_bulkApply ONE of a fixed set of operations to MANY documents at once. Methods: set_correspondent, set_document_type, set_storage_path, add_tag, remove_tag, modify_tags, modify_custom_fields, set_permissions, delete, reprocess, merge, split, rotate, delete_pages, edit_pdf, remove_password. For per-document field edits including title, content, created (date), archive_serial_number, or owner, use update_document instead — those fields are not editable here. Note: 'remove_tag' only removes the tag from the specified documents (tag stays in the system); 'delete_tag' permanently deletes the tag from the entire system. ⚠️ WARNING: method 'delete' permanently deletes documents and requires confirm=true. Select documents either by `documents` (IDs) or by `all: true` + `filters` — Paperless document filter names such as correspondent__id, tags__id__all, document_type__id, title_content, created__date__gte or query (full text); the filter form changes every matching document in one call, e.g. reassigning all documents from a duplicate correspondent before deleting it. Unknown filter keys are refused, and the result reports matched_documents. all=true is not supported for merge, split, delete_pages, edit_pdf or remove_password. Method remove_password strips a PDF password (needs `password`); with update_document=true the unlocked file is stored as a new version of the same document. Method reprocess accepts remote_ocr=true to use the configured remote OCR engine.post_documentUpload a new document file (PDF, image, etc.) to Paperless-NGX with optional metadata. Upload is asynchronous: by default returns a task UUID (use list_tasks to track consumer progress) — the actual document ID is assigned only after the consumer has processed the file. Set poll=true to wait for the consumer to finish and return the final result (the new document_id on success, or the consumer error on failure) in a single call. Optional metadata: title, created (date), correspondent, document_type, storage_path, tags, archive_serial_number, custom_fields.list_documentsList and filter documents by fields such as title, correspondent, document type, tag, storage path, creation date, and more. IMPORTANT: For queries like 'the last 3 contributions' or when searching by tag, correspondent, document type, or storage path, you should FIRST look up the correct ID — get_filing_options returns every tag, correspondent, document type and storage path in one call (or use list_tags / list_correspondents / list_document_types / list_storage_paths) — and then use that ID as a filter here. Only use the 'search' argument for free-text search when no specific field applies. Using the correct ID filter will yield much more accurate results. Note: Document content is excluded from results by default. Use 'get_document_content' to retrieve content when needed. To find near-duplicates of one document use more_like_id; to list everything Paperless has flagged as a duplicate use has_duplicates=true.get_documentGet 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 'get_document_content' to retrieve content when needed. Documents can have several file versions (`versions`; manage them with upload_document_version / update_document_version / delete_document_version). Content (get_document_content) and get_document_metadata follow the LATEST version, but page_count, original_file_name and archived_file_name always describe the ROOT (first) version — e.g. after a password-protected PDF was unlocked into a new version, page_count stays null. Don't use page_count to judge whether a document is readable; check its content.get_document_contentGet the text content of a specific document by ID. Use this when you need to read or analyze the actual document text. For long documents, read a slice with max_chars (and offset to continue) — e.g. max_chars: 2000 is usually enough to identify a document. Paperless stores the text without page boundaries, so slices are by characters, not pages.search_documentsRanked full-text search through Paperless's search index (content, title and metadata). mode 'query' (default) takes advanced syntax — AND/OR/NOT, "quoted phrases", field:value, wildcards*; 'text' takes plain words with no syntax; 'title' searches titles only. The index is updated in the background and can lag behind or miss documents: if you expect matches but get none, use list_documents with `search`, which scans the database directly. For filtering by tag, correspondent, type or date use list_documents. Content is excluded from results; use get_document_content.download_documentDownload a document file by ID. Returns the document as a base64-encoded resource.get_document_thumbnailGet a document thumbnail (image preview) by ID. Returns the thumbnail as a base64-encoded WebP image resource.update_documentUpdate fields on ONE document (PATCH — only fields you supply are changed). To change tags, prefer add_tags / remove_tags: they leave the other tags alone. `tags` REPLACES the whole list — any tag you leave out is removed. Every tag change returns tag_changes {added, removed}. Editable fields: title, correspondent, document_type, storage_path, tags, add_tags, remove_tags, content (raw searchable text), created (document date, YYYY-MM-DD), archive_serial_number, owner, custom_fields. For applying the same change to MANY documents, see edit_documents_bulk. To add a comment/annotation rather than change a field, see create_document_note.email_documentSend a document via email to one or more recipients.get_document_historyGet the change history / audit log for a document, showing who changed what and when.get_document_previewGet a full-page preview image of a document. Returns the preview as a base64-encoded image resource.- +97 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Derive
{
"mcpServers": {
"derive": {
"command": "npx",
"args": [
"-y",
"@derive-to/mcp"
],
"env": {
"DERIVE_SERVER": "YOUR_DERIVE_SERVER_HERE",
"DERIVE_TOKEN": "YOUR_DERIVE_TOKEN_HERE"
}
}
}
}
Paperless Ngx
{
"mcpServers": {
"paperless-ngx-2": {
"command": "npx",
"args": [
"-y",
"paperless-ngx-mcp"
],
"env": {
"PAPERLESS_URL": "YOUR_PAPERLESS_URL_HERE",
"PAPERLESS_API_KEY": "YOUR_PAPERLESS_API_KEY_HERE"
}
}
}
}
Frequently asked questions
Derive is categorized under Developer Tools and uses a local stdio subprocess. Paperless Ngx belongs to Developer Tools and uses a local stdio subprocess. Pick Derive for developer tools work and Paperless Ngx for developer tools.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Derive has no declared pricing — check the project's own site. Paperless Ngx has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add derive and paperless-ngx-2 as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Derive has a quality signal of 64/100 (Good) with 0 views, 0 installs and 30 GitHub stars. Paperless Ngx has 65/100 (Great) with 0 views, 0 installs and 11 GitHub stars.