io.github.shigechika/jquants-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

  warn15% of grade

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

  tests/test_db_users.py: assigns a literal to api_key (jqua…bc (len 15)) — non-provider secret literal; prefer environment intake. tests/test_db_users.py: assigns a literal to api_key (supe…ey (len 16)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. scripts/collect_metrics.py) — the recommended intake shape.

• 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 (scripts/collect_metrics.py: subprocess.* call; scripts/bulk_fetch_all.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (scripts/collect_metrics.py: subprocess.* call; src/jquants_mcp/cli.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: scripts/collect_metrics.py: subprocess.* call discloses broad/destructive filesystem access: src/jquants_mcp/cli.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) 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 1.2.0 (minor bump): new capability primitive(s) in source: fs-write, http-client, subprocess; new hardcoded outbound host/BCC destination(s): 127.0.0.1, accounts.google.com, api.example.com, api.jquants.com, claude.ai, example.com, github.com, jpx-jquants.com, jquants-mcp.example.com, mcp.example.com, monitoring.googleapis.com, oauth2.googleapis.com, your-cloud-run-service.run.app.

• Transport config

  warn10% of grade

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

  manifest/source references telemetry behavior — disclosure