MCP server · trust report

io.github.endoflife-ai/endoflife-mcp

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

Publisher
io.github.endoflife-ai
Repository
github.com/endoflife-ai/endoflife-mcp
Install
remote only
Versions
5
MCP revision
2025-11-25 · superseded
Inspected
6 of 6 checks · 100%
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.

6 checks5 clean1 flagged
  • Injection surface

    pass25% of grade

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

    Scanned 67 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

    pass25% of grade

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

    repository linkage verified

  • 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

    pass15% of grade

    Declared 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

    pass10% of grade

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

    vs prior 1.0.2 (minor bump): tool "get_risk_score" description changed (wording only, no injection pattern); tool "scan_stack" description changed (wording only, no injection pattern); tool "list_products" description changed (wording only, no injection pattern); tool "get_product_lifecycle" description changed (wording only, no injection pattern); new tool "get_kev_exposure" appeared; new tool "get_upcoming_eol" appeared; new tool "get_edge_device_status" appeared; new tool "get_upgrade_path" appeared; new tool "check_sbom" appeared. Low-severity drift (informational; consistent with the version bump).

  • 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
v1.1.0 · current2026-09-03 A906/6 · 100%±0
v1.0.22026-07-29 A905/6 · 90%B→A in v1.0.2
v1.0.12026-07-19 B904/6 · 75%insf→B in v1.0.1
v1.0.02026-06-30 insufficient1/6 · 25%