MCP server · trust report

io.github.musharna/plantcv-mcp

1 check that ran failed — version behavior — so this release can’t be trusted as-is.

Publisher
io.github.musharna
Repository
github.com/musharna/plantcv-mcp
Install
pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp, pypi:plantcv-mcp
Versions
36
Inspected
5 of 6 checks · 75%
Scored
2026-09-04 · rubric 1.0.0

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.

6 checks2 clean3 flagged1 not inspected
  • 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. src/plantcv_mcp/paths.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.

    discloses broad/destructive filesystem access: src/plantcv_mcp/hyperspectral.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/plantcv_mcp/imaging.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/plantcv_mcp/thermal.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 1.13.0 (patch bump): new capability primitive(s) in source: child_process, fs-write, subprocess; new hardcoded outbound host/BCC destination(s): github.com.

  • Transport config

    warn10% of grade

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

    sends telemetry to third-party SDK (amplitude) — disclosure, verify opt-in

Version history

Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.

VersionPublishedGradeScoreInspectedChange
v1.13.1 · current2026-09-03 B77.55/6 · 75%±0
v1.13.02026-09-03 B1004/6 · 65%±0
v1.10.12026-09-02 B1004/6 · 65%±0
v1.8.12026-09-01 B1004/6 · 65%±0
v1.7.02026-08-30 B1004/6 · 65%±0
v1.5.42026-08-29 B1004/6 · 65%±0
v1.5.12026-08-29 B1004/6 · 65%±0
v1.2.02026-08-28 B1004/6 · 65%±0
v0.4.12026-08-02 B1004/6 · 65%±0
v0.3.22026-07-31 B1003/6 · 55%