MCP server · trust report

com.droplinked.mcp/server

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

Publisher
com.droplinked.mcp
Repository
github.com/droplinked/droplinked-mcp
Install
remote only
Versions
3
MCP revision
2025-11-25 · superseded
Inspected
5 of 6 checks · 85%
Scored
2026-09-02 · 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 checks2 clean3 flagged1 not inspected
  • 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 187 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.

    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 "quote_inventory_available" has a secret-shaped input parameter "agentBearer" — secrets must never be tool parameters (the model would supply/handle the credential). tool "process_payment" has a secret-shaped input parameter "agentBearer" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_lending_application_status" has a secret-shaped input parameter "agentBearer" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_document_checklist" has a secret-shaped input parameter "agentBearer" — secrets must never be tool parameters (the model would supply/handle the credential). tool "list_lending_applications_for_merchant" has a secret-shaped input parameter "agentBearer" — secrets must never be tool parameters (the model would supply/handle the credential). tool "request_partner_referral" has a secret-shaped input parameter "agentBearer" — secrets must never be tool parameters (the model would supply/handle the credential). tool "quote_credit_terms" has a secret-shaped input parameter "agentBearer" — secrets must never be tool parameters (the model would supply/handle the credential). tool "find_business_buyer" has a secret-shaped input parameter "agentBearer" — secrets must never be tool parameters (the model would supply/handle the credential). tool "report_repayment" has a secret-shaped input parameter "agentBearer" — secrets must never be tool parameters (the model would supply/handle the credential).

  • Permission scope

    unscannable15% of grade

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

    No source files, package.json, or pyproject were fetched; cannot infer capability scope.

  • 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 0.1.1 (patch bump): new tool "find_merchant" touches a sensitive surface (email/exec/net/fs); new tool "find_inventory" appeared; new tool "find_affiliate_programs" appeared; new tool "verify_brand_attestation" appeared; new tool "request_brand_attestation" appeared; new tool "get_brand_attestation_status" appeared; new tool "verify_credit_risk" appeared; new tool "verify_repayment_history" touches a sensitive surface (email/exec/net/fs); new tool "verify_cross_attestation" appeared; new tool "verify_lender" appeared; new tool "get_lender_history" appeared; new tool "verify_methodology" touches a sensitive surface (email/exec/net/fs); new tool "get_methodology_timeline" appeared; new tool "get_methodology_versions" touches a sensitive surface (email/exec/net/fs); new tool "get_trust_dossier" appeared; new tool "get_trust_fabric_stats" touches a sensitive surface (email/exec/net/fs); new tool "get_underwriting_signals" appeared; new tool "get_upgrade_preview" appeared; new tool "recommend_lender" appeared; new tool "recommend_service_provider" appeared; new tool "quote_inventory_available" appeared; new tool "process_payment" appeared; new tool "search_products" appeared; new tool "get_product" touches a sensitive surface (email/exec/net/fs); new tool "list_shop_products" touches a sensitive surface (email/exec/net/fs); new tool "start_checkout" touches a sensitive surface (email/exec/net/fs); new tool "get_feed" touches a sensitive surface (email/exec/net/fs); new tool "cart.addLine" appeared; new tool "cart.updateLineQuantity" appeared; new tool "cart.removeLine" appeared; new tool "cart.applyDiscount" appeared; new tool "get_lending_application_status" appeared; new tool "get_document_checklist" touches a sensitive surface (email/exec/net/fs); new tool "list_lending_applications_for_merchant" appeared; new tool "request_partner_referral" appeared; new tool "quote_credit_terms" appeared; new tool "find_business_buyer" appeared; new tool "report_repayment" 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)

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
v0.1.2 · current2026-08-01 C655/6 · 85%insf→C in v0.1.2
v0.1.12026-07-01 insufficient2/6 · 35%