Zotero MCP

Overview Schema Source Related Servers Discussions Admin

Zotero Get Item Fulltext

zotero_get_item_fulltext

Reads the complete extracted text of a Zotero item's main PDF or EPUB attachment. Returns large token counts, so call it only to actually read a paper.

Instructions

Return the extracted text of a Zotero item's primary attachment (PDF or EPUB). WARNING: returns most or all of the paper (often 10K+ tokens). Use ONLY when the user explicitly wants to READ the paper — not for searching or browsing. For topic search use zotero_semantic_search; for metadata only use zotero_get_item_metadata. PDFs are read up to fulltext_display_max_pages (10 by default); when that cuts a document short the heading names the page range and TRUNCATED — read on with zotero_read_pdf_pages. Avoid calling this on multiple papers in one conversation unless the user specifically asked to read several. item_key: 8-character Zotero item key. Normally the parent item — the tool locates the attached PDF/EPUB itself, preferring PDF unless attachment_priority says otherwise. Passing an attachment's own key instead reads exactly that file and skips the priority order, which is how you read one specific attachment of an item that has several (find keys via zotero_get_item_children). Scope: active library only. Extraction path (in order): local Zotero storage via SQLite when running in local mode (fastest, respects pdf_max_pages config); Zotero's server-side fulltext index; direct download and parsing as a last resort. Image-only scanned PDFs without OCR may return little or no text. Example: zotero_get_item_fulltext(item_key='RTKZQI8E').

Input Schema

TableJSON Schema

Name	Required	Description	Default
`item_key`	Yes	Zotero item key/ID. Normally the parent item, whose best attachment is chosen by ``attachment_priority``. Passing an attachment's own key is also supported and reads exactly that file, bypassing the priority order — pair it with ``zotero_get_item_children`` to read one specific attachment of an item that has several (#378).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 2, 2026

TDQS

A4.9/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and succeeds. It discloses large token output (often 10K+), truncation behavior with fulltext_display_max_pages, the TRUNCATED heading, follow-up via zotero_read_pdf_pages, extraction path order, and image-only OCR limitations. This goes well beyond what structured fields would reveal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence earns its place: warning, alternatives, truncation behavior, extraction path, attachment semantics, and a final example. The critical warning is front-loaded, and the example anchors correct invocation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, when to use, what to expect, truncation follow-up, attachment priority behavior, library scope, extraction paths, and limitations. Since an output schema exists, return-value shape does not need separate explanation. Nothing essential is missing for an agent to invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema coverage is 100% and already documents parent-item versus attachment-key semantics. The description supplements this with the 8-character key format, PDF preference unless attachment_priority says otherwise, and a concrete pointer to zotero_get_item_children for finding attachment keys. These additions justify a small uplift above the high-coverage baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a precise verb and resource: 'Return the extracted text of a Zotero item's primary attachment (PDF or EPUB).' It also distinguishes itself from siblings by naming zotero_semantic_search and zotero_get_item_metadata, so an agent can tell them apart without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is explicitly gated: 'Use ONLY when the user explicitly wants to READ the paper — not for searching or browsing.' It names the alternatives for topic search and metadata-only requests, and warns against calling it on multiple papers unless the user asked to read several. This is model-ready guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server