MCP server · trust report
io.thegavel/gavel
3 checks that ran failed — credential hygiene, version behavior and transport config — so this release can’t be trusted as-is.
- Publisher
- io.thegavel
- Repository
- github.com/JamieFrame/gavel-mcp
- Install
- remote only
- Versions
- 2
- 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- 2025-11-25 · superseded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.
Injection surface
warn25% of gradeTool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).
tool "list_onchain_indicators" description: off-vendor URL in a description (mcp.bitcoincreditstack.com); capability text should not name where data goes. tool "get_mvrv" description: off-vendor URL in a description (mcp.bitcoincreditstack.com); capability text should not name where data goes. server instructions: off-vendor URL in a description (mcp.bitcoincreditstack.com); capability text should not name where data goes.
Supply chain
warn25% of gradePackage provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.
dependency "viem" is edit-distance 2 from top-20 package "vue" (typosquat candidate)
Credential hygiene
fail15% of gradeHow the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.
tool "prepare_create_auction_calldata" has a secret-shaped input parameter "collateral_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "prepare_create_auction_calldata" has a secret-shaped input parameter "loan_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "prepare_claim_refund_calldata" has a secret-shaped input parameter "token_address" — 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 0.3.0 (minor bump): tool "list_gavel_indicators" description changed (wording only, no injection pattern); tool "get_gavel_indicator" description changed (wording only, no injection pattern); tool "list_onchain_indicators" description changed and now contains embedded outbound URL; tool "get_mvrv" description changed and now contains embedded outbound URL; new hardcoded outbound host/BCC destination(s): api-testnet.thegavel.io, arb1.arbitrum.io, sepolia-rollup.arbitrum.io.
Transport config
fail10% of gradeRemote 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.
| Version | Published | Grade | Score | Inspected | Change |
|---|---|---|---|---|---|
| v0.4.0 · current | 2026-08-29 | D | 40 | 6/6 · 100% | C→D in v0.4.0 |
| v0.3.0 | 2026-08-26 | C | 62.5 | 5/6 · 90% | — |