MCP server · trust report
app.marketgenius/mcp
2 checks that ran failed — version behavior and transport config — so this release can’t be trusted as-is.
- Publisher
- app.marketgenius
- Repository
- —
- Install
- remote only
- Versions
- 87
- Inspected
- 5 of 6 checks · 85%
- Scored
- 2026-07-21 · 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.
Injection surface
pass25% of gradeTool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).
Scanned 248 text field(s); no instruction-injection patterns found. PASS = no static red flag. A server can serve different tool descriptions at runtime (the rug-pull class), which static scanning cannot see.
Supply chain
warn25% of gradePackage 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 gradeHow 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 gradeDeclared 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
fail10% of gradeDiff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).
vs prior 2026-07-18 (other bump): new tool "mg_list" appeared; new tool "mg_calculator_cagr" appeared; new tool "mg_calculator_cagr_update" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_cagr_sync" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_cagr_state" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_dividend" appeared; new tool "mg_calculator_dividend_update" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_dividend_sync" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_dividend_state" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_market_cap" appeared; new tool "mg_calculator_market_cap_update" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_market_cap_sync" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_market_cap_state" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_profit_margin" appeared; new tool "mg_calculator_profit_margin_update" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_profit_margin_sync" touches a sensitive surface (email/exec/net/fs); new tool "mg_calculator_profit_margin_state" touches a sensitive surface (email/exec/net/fs).
Transport config
fail10% of gradeRemote 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.
| Version | Published | Grade | Score | Inspected | Change |
|---|---|---|---|---|---|
| v2026-07-19 · current | 2026-07-19 | C | 67.5 | 5/6 · 85% | insf→C in v2026-07-19 |
| v2026-07-18 | 2026-07-18 | insufficient | — | 1/6 · 25% | B→insf in v2026-07-18 |
| v2026-07-16 | 2026-07-16 | B | 77.5 | 4/6 · 75% | insf→B in v2026-07-16 |
| v2026-05-16 | 2026-05-16 | insufficient | — | 1/6 · 25% | ±0 |
| v2026-05-08 | 2026-05-08 | insufficient | — | 1/6 · 25% | ±0 |
| v2026-05-04 | 2026-05-04 | insufficient | — | 1/6 · 25% | B→insf in v2026-05-04 |
| v2026-04-15 | 2026-04-15 | B | 77.5 | 4/6 · 75% | — |