io.github.54yyyu/zotero-mcp

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

• Injection surface

  unscannable25% of grade

  Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

  No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

• Supply chain

  fail25% of grade

  Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

  Python build script executes at build time: network call in build script

• Credential hygiene

  pass15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  Reads secrets from the environment (e.g. src/zotero_mcp/_app.py) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• Permission scope

  warn15% of grade

  Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

  has both shell/exec and network egress — capable of download-and-run, though no such path was observed (src/zotero_mcp/cli.py: subprocess.* call; src/zotero_mcp/better_bibtex_client.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (src/zotero_mcp/cli.py: subprocess.* call; src/zotero_mcp/cli.py: open(…, 'w'/'a'/'x') write-mode file access). discloses shell/exec capability: 6 files (src/zotero_mcp/cli.py, src/zotero_mcp/local_db.py, src/zotero_mcp/pdfannots_helper.py, +3 more) discloses broad/destructive filesystem access: 14 files (src/zotero_mcp/cli.py, src/zotero_mcp/cli.py, src/zotero_mcp/openai_batch.py, +11 more) Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

• Version behavior

  fail10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  vs prior 0.10.0 (minor bump): new capability primitive(s) in source: dynamic-eval, fs-write, http-client, subprocess; new hardcoded outbound host/BCC destination(s): 10.0.0.5, 127.0.0.1, 169.254.169.254, a9.com, alt.example.com, api.crossref.org, api.github.com, api.openalex.org, api.scite.ai, api.semanticscholar.org, api.unpaywall.org, api.zotero.org, arxiv.org, aurimasv.github.io, books.google.com, dav.example.com, doi.org, dx.doi.org, evil.example, example.com, example.org, example.test, export.arxiv.org, github.com, isbndb.com, landing.example.com, new.example.com, old.example.com, openalex.org, openlibrary.org, platform.openai.com, pmc.ncbi.nlm.nih.gov, pypi.org, retorque.re, s2.example.com, scite.ai, stevenyuyy.com, www.googleapis.com, www.idpf.org, www.w3.org, www.zotero.org, x.com, zotero, zotero.org.

• Transport config

  fail10% of grade

  Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

  source performs runtime self-update / download-and-execute (bypasses version_behavior); manifest/source references check for updates behavior — disclosure