Cite Caddy vs Paperboy — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Cite Caddy vs Paperboy
In-depth architectural comparison of the Cite Caddy and Paperboy MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Cite Caddy
Research · Local stdio
Quality: 44/100 (Fair) | Auth: No auth required
Paperboy
Research · Local stdio
Quality: 52/100 (Good) | Auth: other
Verdict Summary: Choose Cite Caddy if you need specialized Research tools running via a local process. Choose Paperboy if your workspace requires Research integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Cite Caddy when:
You need dedicated capabilities in the Research domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
You have access to required keys: ZOTERO_LIBRARY_ID, ZOTERO_LIBRARY_TYPE, ZOTERO_API_KEY, MCP_TOKEN_STORE_KEY, MCP_PUBLIC_URL, MCP_DATA_DIR.
Remote MCP server for full read/write access to a Zotero library
Send research papers from Claude to a Kindle or Kobo, with Zotero as the source of truth. Searches arXiv and OpenAlex, recommends related work via the Semantic Scholar citation graph, queues papers in a Zotero collection, and delivers the PDFs by email or Dropbox. Receipts report file sizes and name anything that could not be sent.
query` defaults to Zotero's quick search (title/creator/year); `full_text=True` also matches indexed content of attached files/notes (`qmode="everything"`), requires non-empty `query`. Each result's `creators` is a list of `{creatorType, firstName, lastName}` (or `{creatorType, name}` for single-fi…
get_item
creators` shape as above.
list_collections
list_tags
list_trash
creators` shape as above.
list_saved_searches
list_groups
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Cite Caddy is categorized under Research and uses a local stdio subprocess. In contrast, Paperboy belongs to Research using local stdio subprocess. Select Cite Caddy when you need capabilities focused on research and Paperboy when you require tools for research.
id` doubles as `target_library_id` (with `target_library_type="group"`) for `move_item_to_different_library`.
list_item_types
list_item_fields
list_item_type_fields
Check before `create_item`/`update_item` instead of guessing — what fields a given `item_type` accepts.
list_item_creator_types
Same, for `creators` entries' `creatorType`.
list_creator_fields
Name-shape fields (`firstName`, `lastName`, `name`, ...) valid on a `creators` entry itself — not the same as `list_item_creator_types` (roles).
+27 more tools listed on main page
Paperboy Tools (14)
search_papers
Search OpenAlex (general) or arXiv (`source="arxiv"`); results carry a `ref` and an `open_access_pdf` flag
recommend_papers
Discover related or new papers: citation-graph recommendations (Semantic Scholar) seeded from your Zotero library, plus keyword discovery from interests Claude distills out of the conversation. Excludes papers you already have
send_papers
One-off send by arXiv id, DOI, URL, or title (also records in Zotero if configured)
queue_papers
Add papers to the Zotero Reading Queue without sending (optionally filed into topical collections)
add_to_library
Track papers in Zotero **without** queueing or sending them (owned, paywalled, or read-later); a missing OA PDF is not treated as a failure
add_book
Catalogue a book by ISBN, book DOI, or title as a Zotero `book` item (Crossref, Open Library, Google Books); never delivered
attach_pdf
Ingest a PDF you already have (grey literature, open-access textbooks) with the PDF attached and metadata you supply; optionally send it
list_collections
List Zotero collections so Claude can propose where to file a paper, or ask you
file_papers
File queued papers into a topical collection (created on demand; queue membership unaffected)
unfile_papers
Remove papers from one collection (for misfiled items); the papers themselves and their queue/sent state are untouched
list_queue
Show the queue with per-item status (unsent / sent / no-open-access-pdf)