MCP server · trust report

com.santismm/knowledge

3 checks that ran failed — injection surface, version behavior and transport config — so this release can’t be trusted as-is.

Publisher
com.santismm
Repository
github.com/santismm/santismm-knowledge-mcp
Install
remote only
Versions
4
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2025-11-25 · superseded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 checks2 clean4 flagged
  • Injection surface

    fail25% of grade

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

    resource "handbook/HRN-011@en" description: names an outbound copy/exfil destination (BCC/exfil verb).

  • Supply chain

    warn25% of grade

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

    dependency "@modelcontextprotocol/server" is edit-distance 1 from popular package "semver" (typosquat candidate)

  • 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

    fail10% of grade

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

    vs prior 0.2.1 (minor bump): tool "calculate_agent_economics" gained input property(ies): locale; tool "calculate_evaluation_sample_size" gained input property(ies): locale; tool "calculate_human_supervision_capacity" gained input property(ies): locale; new hardcoded outbound host/BCC destination(s): github.com, santismm.com.

  • 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
v0.4.1 · current2026-09-02 D42.56/6 · 100%C→D in v0.4.1
v0.2.12026-08-02 C67.56/6 · 100%B→C in v0.2.1
v0.2.02026-08-01 B904/6 · 75%