io.github.jurimaxam-dotcom/chemdraw-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

  pass25% of grade

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

  Python build script has no build-time network/exec; repository linkage verified

• 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. chemdraw_tool/resolver.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.

  installer script pipes a download into a shell — conventional, but worth reading before running (install.sh: pipes a download into a shell). has both shell/exec and network egress — capable of download-and-run, though no such path was observed (chemdraw_tool/chemdraw.py: subprocess.* call; chemdraw_tool/anki_export.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (chemdraw_tool/chemdraw.py: subprocess.* call; scripts/gen_3d_gif.sh: open(…, 'w'/'a'/'x') write-mode file access). discloses shell/exec capability: chemdraw_tool/chemdraw.py: subprocess.* call discloses shell/exec capability: chemdraw_tool/resolver.py: subprocess.* call discloses broad/destructive filesystem access: scripts/gen_3d_gif.sh: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: scripts/gen_mechanism_gif.sh: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: scripts/gen_titrations.py: open(…, 'w'/'a'/'x') write-mode file access 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 0.2.0 (minor bump): new capability primitive(s) in source: child_process, fs-write, http-client, subprocess; new hardcoded outbound host/BCC destination(s): 127.0.0.1, astral.sh, cactus.nci.nih.gov, docs.astral.sh, github.com, pubchem.ncbi.nlm.nih.gov, rest.kegg.jp, rest.uniprot.org, www.ebi.ac.uk, www.kegg.jp, www.uniprot.org.

• Transport config

  unscannable10% of grade

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

  local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.