Skills/PyPI/zra-mcp

zra-mcp@0.4.9

VERIFIED· not started

Publisher claims: "AI-powered Zotero research assistant — a standalone MCP server with 36 tools for literature search, bilingual retrieval, reading analysis, citation management, and review writing." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher qiobn · publishing for 171 daysInstalls 0Last detonated 1 h ago
$claude mcp add zra-mcp -- uvx zra-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
CORE_API_KEYEVA_JUDGE_API_KEYTWINE_PASSWORDZOTERO_API_KEYConfiguration, not credentials: CHROMA_PERSIST_DIR, CNKI_ENABLED, EMBEDDING_BACKEND, EMBEDDING_BATCH_SIZE, EMBEDDING_DEVICE, EMBEDDING_MAX_SEQ_LEN, EMBEDDING_MODEL, EVA_JUDGE_API_BASE, EVA_JUDGE_MAX_RETRIES, EVA_JUDGE_MODEL, EVA_JUDGE_TEMPERATURE, EVA_JUDGE_TIMEOUT_MS, HF_ENDPOINT, HF_HUB_OFFLINE, OPENALEX_MAILTO, RERANKER_MODEL, UNPAYWALL_EMAIL, ZOTERO_LIBRARY_ID, ZOTERO_LIBRARY_TYPE, ZOTERO_LOCAL, ZRA_ANNOTATION_SCAN_CAP, ZRA_AUTO_SYNC, ZRA_CHROMA_HOST, ZRA_CHROMA_MODE, ZRA_CHROMA_PORT, ZRA_CLEAN_ENABLED, ZRA_HNSW_CONSTRUCTION_EF, ZRA_HNSW_M, ZRA_HNSW_SEARCH_EF, ZRA_INDEX_BILINGUAL_ENRICHMENT, ZRA_NMT_CACHE_DIR, ZRA_RETRIEVAL_LOG, ZRA_SKILLS_DIR, ZRA_SYNC_WORKERS, ZRA_ZOTERO_TIMEOUT
Where it talks to
no vendor host named in the codeAlso zotero.org, openalex.org, doi.org, arxiv.org, hf-mirror.com, crossref.org, semanticscholar.org, openlibrary.org, unpaywall.org, nih.gov, core.ac.uk — 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 zotero.org, openalex.org, doi.org, arxiv.org, hf-mirror.com, crossref.org, semanticscholar.org, openlibrary.org, unpaywall.org, nih.gov, core.ac.uk as well as its own vendor. The guard injects CORE_API_KEY, EVA_JUDGE_API_KEY, TWINE_PASSWORD, ZOTERO_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx zra-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 83/100 (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
0.2sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsCLAUDE.md:93 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Defaults are zero-config: users should get basic functionality without any `.env` editsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsCLAUDE.md:91 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- `.env` is gitignored; `.env.example` is committed (template only, no real secrets)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsresearch_core/tools/health.py:348 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Review .env file. Most issues resolve "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/run_recall_evaluation.py:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load .env before any project importsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/run_recall_evaluation.py:33 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(Path(__file__).resolve().parent.parent / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsCLAUDE.md:94 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- New env vars must be documented in: `.env.example`, both READMEs' config tablesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/DEVELOPMENT_LOG_EN.md:574 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- Evaluate whether to update this file + `CHANGELOG.md` on every commit (see `CLAUDE.md` rules)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsscripts/run_strategy_eval.py:226 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(Path(__file__).resolve().parent.parent / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsresearch_core/tools/search.py:588 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"ZOTERO_API_KEY and ZOTERO_LIBRARY_ID to your .env file."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsresearch_core/rag/embedding.py:55 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"HF_ENDPOINT=https://hf-mirror.com in your .env file and retry."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsresearch_core/tools/manage.py:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"and ZOTERO_LIBRARY_ID to your .env file (get them at "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsresearch_core/tools/health.py:176 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"ZOTERO_LIBRARY_ID in .env. Get your key at "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsproject_a_mcp/server.py:285 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"log in to CNKI, set CNKI_ENABLED=true in .env, restart MCP).\n\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/compare_output_formats.py:291 · File type combined with upload action — agent may exfiltrate local data filesprint(f'Files written to scripts/output_old.json, output_new.json, output_context_block.md')Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsproject_a_mcp/server.py:555 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Check CHROMA_PERSIST_DIR in .env and ensure the directory is writable."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsresearch_core/tools/health.py:108 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"fix": "Check .env configuration (ZOTERO_LOCAL=true).",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsresearch_core/tools/health.py:268 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"国内用户 / China users: set HF_ENDPOINT=https://hf-mirror.com in .env."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsproject_a_mcp/server.py:495 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"建议 / Suggestion: 检查 .env 中的 ZOTERO_API_KEY。\n"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionscripts/generate_eval_queries.py:11 · File type combined with upload action — agent may exfiltrate local data filespython scripts/generate_eval_queries.py --output my.json # Custom output pathFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Access to sensitive file pathsscripts/index_library.py:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(_project_root / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsproject_a_mcp/server.py:507 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"建议 / Suggestion: 在 .env 中配置 ZOTERO_API_KEY 和 ZOTERO_LIBRARY_ID 以启用写入。"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandscripts/publish.sh:85 · File permission modification command — agent changes file ownership/permissions- Create ~/.pypirc (chmod 600) with your PyPI API token (see header of this script).Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsscripts/index_library.py:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load .env from project root so the script works standalone (not just via MCP)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsresearch_core/zotero/client.py:175 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"and ZOTERO_LIBRARY_ID in .env. Reads will stay local (fast), writes "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/index_sample.py:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(_project_root / ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandscripts/publish.sh:8 · File permission modification command — agent changes file ownership/permissions# 2. ~/.pypirc (recommended — keep it chmod 600)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsproject_a_mcp/server.py:538 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Please ensure Zotero is running and .env is correctly configured."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsresearch_core/tools/health.py:191 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"fix": "Check CHROMA_PERSIST_DIR in .env and ensure the directory is writable.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsCLAUDE.md:103 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files5. `.env.example` — new env vars with commentsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/rebuild_index.py:19 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_dotenv(".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈1,610 tok
2 files · 81 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 zra-mcp@0.4.9 as of 47 min ago. This is the package itself, not its dependencies.