io.github.TotesMagotes/mcp-server-auth

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

  fail25% of grade

  Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

  tool "send_report_to_accounting" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "correct_expenses" description: off-vendor URL in a description (www.expensebot.ai); capability text should not name where data goes.

• Supply chain

  pass25% of grade

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

  repository linkage verified

• Credential hygiene

  pass15% of grade

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

  Reads secrets from the environment (e.g. src/client.js) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• Permission scope

  pass15% of grade

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

  Network egress present (src/client.js: 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 0.6.20 (patch bump): tool "create_report" description changed (wording only, no injection pattern); tool "create_report" gained input property(ies): recipientRole; tool "share_report" description changed (wording only, no injection pattern); tool "share_report" gained input property(ies): recipientRole; tool "search_knowledge" description changed (wording only, no injection pattern); tool "submit_receipt" description changed (wording only, no injection pattern); tool "submit_receipt" gained input property(ies): photoBase64; tool "get_last_receipt_result" description changed (wording only, no injection pattern); tool "add_income_from_file" gained input property(ies): photoBase64; tool "add_income_from_csv" gained input property(ies): csvText; tool "get_accounting_integration_status" description changed (wording only, no injection pattern); tool "send_report_to_accounting" description changed (wording only, no injection pattern); tool "get_accounting_push_status" description changed (wording only, no injection pattern); tool "get_spreadsheet_url" description changed (wording only, no injection pattern); tool "list_client_invoices" description changed (wording only, no injection pattern); tool "get_client_advance_balances" description changed (wording only, no injection pattern); new tool "request_accounting_integration" touches a sensitive surface (email/exec/net/fs); new tool "get_client_invoice" touches a sensitive surface (email/exec/net/fs); new tool "prepare_client_invoice" touches a sensitive surface (email/exec/net/fs); new tool "create_client_invoice" touches a sensitive surface (email/exec/net/fs); new tool "mark_client_invoice_paid" appeared; new capability primitive(s) in source: http-client; new hardcoded outbound host/BCC destination(s): www.expensebot.ai.

• Transport config

  warn10% of grade

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

  manifest/source references analytics behavior — disclosure