MCP server · trust report

ai.khwan/khwan-mcp

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

Publisher
ai.khwan
Repository
github.com/khwanlabs/khwan-mcp
Install
pypi:khwan-mcp, pypi:khwan-mcp, pypi:khwan-mcp, pypi:khwan-mcp, pypi:khwan-mcp, pypi:khwan-mcp, pypi:khwan-mcp, pypi:khwan-mcp, pypi:khwan-mcp
Versions
9
Inspected
6 of 6 checks · 100%
Scored
2026-08-31 · 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 checks4 clean2 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 20 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.

    Python build script has no build-time network/exec; repository linkage verified

  • Credential hygiene

    fail15% of grade

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

    tool "khwan_record" has a secret-shaped input parameter "turn_token" — secrets must never be tool parameters (the model would supply/handle the credential).

  • 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 0.3.11 (patch bump): new tool "khwan_prepare" appeared; new tool "khwan_record" appeared; new tool "khwan_recall" touches a sensitive surface (email/exec/net/fs); new tool "khwan_remember" touches a sensitive surface (email/exec/net/fs); new tool "khwan_memory" touches a sensitive surface (email/exec/net/fs); new tool "khwan_cores" touches a sensitive surface (email/exec/net/fs).

  • Transport config

    pass10% of grade

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

    remote endpoint "https://mcp.khwan.ai/mcp/{core}/{user}" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)

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
v0.3.12 · current2026-08-27 B756/6 · 100%±0
v0.3.112026-08-27 B1005/6 · 75%±0
v0.3.62026-08-26 B1003/6 · 55%