MCPgrade

MCP server · trust report

io.github.schemacrawler/schemacrawler-ai

Published by io.github.schemacrawler

version-control

Only 2 of 6 checks could run, which is below the bar to certify — nothing that ran raised a red flag.

Publisher
io.github.schemacrawler
Repository
github.com/schemacrawler/SchemaCrawler-AI
Install
oci:docker.io/schemacrawler/schemacrawler-ai:v16.28.1-2, oci:docker.io/schemacrawler/schemacrawler-ai:v16.28.2-1, oci:docker.io/schemacrawler/schemacrawler-ai:v16.28.3-1, oci:docker.io/schemacrawler/schemacrawler-ai:v16.29.1-1, oci:docker.io/schemacrawler/schemacrawler-ai:v17.1.4-1, oci:docker.io/schemacrawler/schemacrawler-ai:v17.1.5-1, oci:docker.io/schemacrawler/schemacrawler-ai:v17.1.5-2, oci:docker.io/schemacrawler/schemacrawler-ai:v17.1.6-1, oci:docker.io/schemacrawler/schemacrawler-ai:v17.1.6-2, oci:docker.io/schemacrawler/schemacrawler-ai:v17.1.7-1, oci:docker.io/schemacrawler/schemacrawler-ai:v17.1.7-3, oci:schemacrawler/schemacrawler-ai:17.10.0-1, oci:schemacrawler/schemacrawler-ai:17.10.1-1, oci:schemacrawler/schemacrawler-ai:17.10.2-1, oci:schemacrawler/schemacrawler-ai:17.11.0-1, oci:schemacrawler/schemacrawler-ai:17.11.0-2, oci:schemacrawler/schemacrawler-ai:17.11.1-1, oci:schemacrawler/schemacrawler-ai:17.11.2-1, oci:schemacrawler/schemacrawler-ai:17.11.2-2, oci:schemacrawler/schemacrawler-ai:17.11.3-1, oci:schemacrawler/schemacrawler-ai:17.11.3-2, oci:schemacrawler/schemacrawler-ai:17.11.4-1, oci:schemacrawler/schemacrawler-ai:17.11.4-2, oci:schemacrawler/schemacrawler-ai:17.11.4-3, oci:schemacrawler/schemacrawler-ai:17.12.1-1, oci:docker.io/schemacrawler/schemacrawler-ai:v17.3.0-1, oci:schemacrawler/schemacrawler-ai:17.5.0-1, oci:schemacrawler/schemacrawler-ai:17.6.0-1, oci:schemacrawler/schemacrawler-ai:17.6.2-1, oci:schemacrawler/schemacrawler-ai:17.6.3-1, oci:schemacrawler/schemacrawler-ai:17.7.0-1, oci:schemacrawler/schemacrawler-ai:17.8.0-1, oci:schemacrawler/schemacrawler-ai:17.8.1-1, oci:schemacrawler/schemacrawler-ai:17.9.0-1, oci:schemacrawler/schemacrawler-ai:17.12.2-1
Versions
36
Inspected
2 of 6 checks · 35%
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.

6 checks2 clean4 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

    pass25% of grade

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

    repository linkage verified

  • Credential hygiene

    unscannable15% of grade

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

    No source files, package manifest, or tool schemas were fetched; cannot assess credential handling.

  • 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

    pass10% of grade

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

    tool surface, capabilities, install scripts, and publisher unchanged vs prior version v17.12.1-1 (patch bump); no rug-pull drift.

  • Transport config

    unscannable10% of grade

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

    local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.

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
vv17.12.2-1 · current2026-07-20 insufficient—2/6 · 35%±0
vv17.12.1-12026-07-15 insufficient—1/6 · 25%±0
vv17.11.4-22026-06-28 insufficient—1/6 · 25%—