io.github.soluai-spa/solucortex-mcp

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

  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 (solucortex.ai); capability text should not name where data goes.

• Supply chain

  fail25% of grade

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

  Python build script executes at build time: network call in build script

• Credential hygiene

  warn15% of grade

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

  tests/test_hardening.py: assigns a literal to secret (scx_…og (len 31)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. src/solucortex_mcp/server.py) — the recommended intake shape.

• Permission scope

  pass15% of grade

  Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

  Network egress present (src/solucortex_mcp/server.py: outbound HTTP/socket call) — expected for most servers and not a finding on its own. 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 1.0.0 (minor bump): new tool "solucortex_recall" appeared; new tool "solucortex_search" appeared; new tool "solucortex_remember" touches a sensitive surface (email/exec/net/fs); new tool "solucortex_update_memory" appeared; new tool "solucortex_flag_memory" appeared; new tool "solucortex_list_memories" appeared; new capability primitive(s) in source: http-client, net; new hardcoded outbound host/BCC destination(s): 127.0.0.1, github.com, solucortex.ai, solucortex.ai..

• 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)