MCP server · trust report

com.accountingqb/accountingqb

2 checks that ran failed — supply chain and version behavior — so this release can’t be trusted as-is.

Publisher
com.accountingqb
Repository
github.com/RCOLKITT/AccountingQB-MCP
Install
remote only
Versions
33
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

    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. setup.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 (setup.py: subprocess.* call; setup.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (setup.py: subprocess.* call; setup.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: setup.py: subprocess.* call discloses broad/destructive filesystem access: setup.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 3.13.0 (minor bump): new capability primitive(s) in source: http-client, subprocess; new hardcoded outbound host/BCC destination(s): appcenter.intuit.com, developer.intuit.com, github.com, oauth.platform.intuit.com.

  • Transport config

    pass10% of grade

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

    remote endpoint "https://mcp.accountingqb.com/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)

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
v3.16.0 · current2026-08-03 D57.55/6 · 75%B→D in v3.16.0
v3.13.02026-08-02 B754/6 · 65%C→B in v3.13.0
v3.7.02026-08-01 C67.55/6 · 75%±0
v3.5.22026-07-28 C67.54/6 · 65%D→C in v3.5.2
v3.5.12026-07-23 D57.55/6 · 75%insf→D in v3.5.1
v3.5.02026-07-21 insufficient2/6 · 35%±0
v3.3.02026-07-13 insufficient2/6 · 35%