MCP server · trust report

com.mart402/extract

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

Publisher
com.mart402
Repository
Install
remote only
Versions
2
MCP revision
2025-06-18 · superseded
Inspected
5 of 6 checks · 85%
Scored
2026-09-01 · 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 checks1 clean4 flagged1 not inspected
  • Injection surface

    warn25% of grade

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

    server instructions: off-vendor URL in a description (mart402.com); capability text should not name where data goes.

  • Supply chain

    warn25% of grade

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

    no resolvable repository linked to the package (provenance unverifiable)

  • Credential hygiene

    pass15% of grade

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

    No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

  • Permission scope

    unscannable15% of grade

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

    No source files, package.json, or pyproject were fetched; cannot infer capability scope.

  • Version behavior

    warn10% of grade

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

    vs prior 0.1.0 (minor bump): tool "extract_url" description changed (wording only, no injection pattern); tool "ocr_image" description changed (wording only, no injection pattern); tool "verify_invoice" description changed (wording only, no injection pattern); tool "enrich_company" description changed (wording only, no injection pattern); tool "structured_extract" description changed (wording only, no injection pattern); tool "jp_company_profile" description changed (wording only, no injection pattern); new tool "get_sample" appeared; new tool "portrait_precheck" appeared; new tool "operator_history" appeared; new tool "document_pipeline" appeared; new tool "pdf_merge" appeared; new tool "pdf_pages" appeared; new tool "pdf_info" appeared; new tool "meal_vision" touches a sensitive surface (email/exec/net/fs); new tool "style_profile" appeared; new tool "style_report" appeared; new tool "report_pack" appeared; new tool "portrait_analysis" appeared; new tool "jp_payroll_net" appeared; new tool "jp_bonus_net" appeared; new tool "jp_social_insurance" appeared; new tool "jp_dependent_threshold" appeared; new tool "jp_consumption_tax" appeared; new tool "jp_business_days" appeared; new tool "jp_overtime_wage" appeared; new tool "jp_retirement_tax" appeared; new tool "jp_mortgage" appeared; new tool "jp_payslip_audit" appeared; new tool "jp_crypto_tax" appeared; new tool "jp_payroll_suite" appeared.

  • Transport config

    fail10% of grade

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

    remote MCP endpoint declares NO authentication (unauthenticated remote — nginx-ui/CVE-2026-33032 class)

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
v0.2.0 · current2026-07-31 C605/6 · 85%±0
v0.1.02026-07-20 C654/6 · 75%