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.
Injection surface
pass25% of gradeTool 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 gradePackage 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 gradeHow 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 gradeDeclared 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 gradeDiff 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 gradeRemote 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.
| Version | Published | Grade | Score | Inspected | Change |
|---|---|---|---|---|---|
| v0.3.12 · current | 2026-08-27 | B | 75 | 6/6 · 100% | ±0 |
| v0.3.11 | 2026-08-27 | B | 100 | 5/6 · 75% | ±0 |
| v0.3.6 | 2026-08-26 | B | 100 | 3/6 · 55% | — |