io.github.lonniev/cypher-mcp

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 grade

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

  Scanned 603 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

  fail25% of grade

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

  Python build script executes at build time: network call in build script

• Credential hygiene

  fail15% of grade

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

  tool "cypher_check_balance" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_purchase_credits" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_check_payment" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_restore_credits" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_account_statement" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_account_statement_infographic" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_report_issue" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_get_patron_onboarding_status" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_receive_credentials" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_receive_credentials" has a secret-shaped input parameter "credential_card" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_forget_credentials" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_update_patron_credential" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_delete_patron_credential" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_get_patron_credential_fields" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_receive_npub_proof" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_check_proof_status" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_set_pricing_model" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_reset_pricing_model" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_request_adoption" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_adoption_status" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_restore_neon_schema" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_check_price" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_mint_coupon" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_list_coupons" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_update_coupon" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_delete_coupon" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_redeem_coupon" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_list_my_coupons" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_forget_coupon" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_execute_query_by_key" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_create_query" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_update_query" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_get_query" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_list_queries" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_delete_query" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_publish_tool" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_unpublish_tool" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_anchor_symbol" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_assert_invariant" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_assert_rationale" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_authorize_capability_why" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_bind_capability_to_symbol" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_bind_rationale_to_symbol" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_capability_patents" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_context_pack" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_explain_capability" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_explain_patent_element" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_factory_resolution_stats" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_find_airline_flights" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_guard_invariant_symbol" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_index_symbol" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_issue_provenance" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_link_capability_consumer" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_link_capability_to_patent" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_link_invariant_to_patent" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_link_issue_to_capability" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_link_pr" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_link_root_cause" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_list_capabilities" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_note_rejection" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_record_scope" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_record_triage" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_register_service" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_suggest_capability_why" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_symbols_in_service" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_upsert_capability" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_upsert_patent_element" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_what_realizes_capability" has a secret-shaped input parameter "dpop_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "cypher_which_service_handles" has a secret-shaped input parameter "dpop_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.

  Network egress present (pyproject declares an HTTP client dependency) — 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

  unscannable10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  no prior version to diff (first sight of io.github.lonniev/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.

• 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)