Skills/PyPI/zotero-library-mcp

zotero-library-mcp@0.10.2

VERIFIED· not started

Publisher claims: "MCP server for searching, reading, annotating, and managing Zotero libraries" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher raulsimpetru · publishing for 264 daysInstalls 322Last detonated 1 h ago
$claude mcp add zotero-library-mcp -- uvx zotero-library-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
ZOTERO_API_KEYZOTERO_MCP_OAUTH_ISSUERZOTERO_MCP_OAUTH_JWKS_URLZOTERO_MCP_OAUTH_RESOURCEZOTERO_WEBDAV_PASSWORD or --allow-unauthenticated-httpConfiguration, not credentials: CROSSREF_MAILTO, UNPAYWALL_EMAIL, ZOTERO_LIBRARY_ID, ZOTERO_LIBRARY_TYPE, ZOTERO_MCP_HOST, ZOTERO_MCP_HTTP_PATH, ZOTERO_MCP_PORT, ZOTERO_MCP_TRANSPORT, ZOTERO_WEBDAV_URL, ZOTERO_WEBDAV_USER
Where it talks to
no vendor host named in the codeAlso arxiv.org, zotero.org, doi.org, crossref.org, unpaywall.org, openlibrary.org — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names arxiv.org, zotero.org, doi.org, crossref.org, unpaywall.org, openlibrary.org as well as its own vendor. The guard injects ZOTERO_API_KEY, ZOTERO_MCP_OAUTH_ISSUER, ZOTERO_MCP_OAUTH_JWKS_URL, ZOTERO_MCP_OAUTH_RESOURCE, ZOTERO_WEBDAV_PASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx zotero-library-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-22 and scored it 91/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

LOW
Authorization escalation languageREADME.md:200 · Authorization escalation language · informational: not an instruction file…mple.com ``` The MCP endpoint is `https://your-tunnel.example.com/mcp`. Enable developer mode in ChatGPT, create a developer-mode app, and enter that URL as the MCP server U…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionREADME.md:200 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…mple.com ``` The MCP endpoint is `https://your-tunnel.example.com/mcp`. Enable developer mode in ChatGPT, create a developer-mode app, and enter that URL as the MCP server U…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedtests/test_mcp_clients.py:19 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionREADME.md:187 · Prompt injection — known jailbreak technique reference · informational: not an instruction file### ChatGPT on the web (Apps SDK / developer mode)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:187 · Authorization escalation language · informational: not an instruction file### ChatGPT on the web (Apps SDK / developer mode)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Context shift attemptREADME.md:200 · Context shift attempt — trying to change operational mode · informational: not an instruction file…nel.example.com ``` The MCP endpoint is `https://your-tunnel.example.com/mcp`. Enable developer mode in ChatGPT, create a developer-mode app, and enter that URL as the MCP server U…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈59 tok
1 file · 34 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for zotero-library-mcp@0.10.2 as of 31 min ago. This is the package itself, not its dependencies.