MCP server · trust report

io.github.cyanheads/smithsonian-mcp-server

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

Publisher
io.github.cyanheads
Repository
github.com/cyanheads/smithsonian-mcp-server
Install
npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server, npm:@cyanheads/smithsonian-mcp-server
Versions
18
Inspected
6 of 6 checks · 100%
Scored
2026-07-20 · 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 checks3 clean3 flagged
  • Injection surface

    warn25% of grade

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

    server instructions: off-vendor URL in a description (api.data.gov); capability text should not name where data goes.

  • 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

    fail10% of grade

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

    vs prior 0.1.16 (patch bump): new tool "smithsonian_search" touches a sensitive surface (email/exec/net/fs); new tool "smithsonian_list_terms" appeared; new tool "smithsonian_get_object" touches a sensitive surface (email/exec/net/fs); new tool "smithsonian_get_media" appeared; new tool "smithsonian_explore" appeared; new tool "smithsonian_find_related" appeared.

  • 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); manifest/source references Telemetry 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.

VersionPublishedGradeScoreInspectedChange
v0.1.17 · current2026-07-19 C67.56/6 · 100%B→C in v0.1.17
v0.1.162026-07-19 B955/6 · 75%±0
v0.1.152026-07-11 B954/6 · 65%