de.agentview/agentview-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

  warn25% of grade

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

  tool "send_url" param "url" description: off-vendor URL in a description (example.com); capability text should not name where data goes. tool "pair_by_code" description: off-vendor URL in a description (display.agentview.de); capability text should not name where data goes. server instructions: off-vendor URL in a description (display.agentview.de); capability text should not name where data goes.

• Supply chain

  warn25% of grade

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

  no resolvable repository linked to the package (provenance unverifiable)

• Credential hygiene

  fail15% of grade

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

  tool "assign_display_categories" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "list_data_slots" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "set_display_grant" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "authenticate" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "create_api_key" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_data_slot" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_storage_usage" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "broadcast_content" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "manage_licenses" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_display" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "send_store_template_to_display" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "create_display" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "delete_data_slot" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_license_info" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_organization" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "remove_display_from_org" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "set_data_slot" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "submit_feedback" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "upload_asset" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "configure_display" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "claim_display" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "send_url" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "clear_display" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_account" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "delete_asset" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "send_html" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "delete_display" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "pair_by_code" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "list_displays" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "list_assets" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_agent_artifact" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "configure_organization" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "list_api_keys" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "read_display_html" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "list_organizations" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "revoke_api_key" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_display_preview_url" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "delete_organization" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "list_display_categories" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "update_asset" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "create_organization" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_asset" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "manage_display_category" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "test_display_content" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_store_template_install_options" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "manage_org_member" has a secret-shaped input parameter "access_token" — 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

  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 de.agentview/[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

  pass10% of grade

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

  remote endpoint "https://agentview.de/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)