1 check that ran failed — version behavior — so this release can’t be trusted as-is.
- Publisher
- io.github.mhajder
- Repository
- github.com/mhajder/ghostfolio-mcp
- Install
- pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.2.0, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.2.1, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.3.0, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.4.0, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.4.1, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.4.2, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.4.3, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.5.0, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.6.0, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.6.1, pypi:ghostfolio-mcp, oci:ghcr.io/mhajder/ghostfolio-mcp:1.6.2
- Versions
- 11
- Inspected
- 5 of 6 checks · 75%
- Scored
- 2026-09-03 · 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
unscannable25% of gradeTool 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 gradePackage 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 gradeHow the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.
Reads secrets from the environment (e.g. src/ghostfolio_mcp/ghostfolio_client.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
pass15% of gradeDeclared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.
No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.
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 1.6.1 (patch bump): new capability primitive(s) in source: http-client; new hardcoded outbound host/BCC destination(s): domain.tld, example.com, ghostfolio-mcp.example.com, ghostfolio.test, github.com, id.example.com, mcp.example.com, your-key.
Transport config
warn10% of gradeRemote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.
sends telemetry to third-party SDK (sentry.io) — disclosure, verify opt-in; manifest/source references tracking behavior — disclosure
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 |
|---|---|---|---|---|---|
| v1.6.2 · current | 2026-09-02 | B | 85 | 5/6 · 75% | ±0 |
| v1.6.1 | 2026-08-27 | B | 75 | 4/6 · 65% | ±0 |
| v1.6.0 | 2026-08-19 | B | 75 | 4/6 · 65% | ±0 |
| v1.5.0 | 2026-07-14 | B | 95 | 5/6 · 75% | C→B in v1.5.0 |
| v1.4.3 | 2026-07-06 | C | 70 | 4/6 · 65% | ±0 |
| v1.4.0 | 2026-05-11 | C | 70 | 4/6 · 65% | — |