co.civai.nova/mcp-bgpt-chowdeck

None of its 24 tools are described as changing anything. For 24 the reading was uncertain, so no mark is shown.

• request_login_otp

  “Send ChowDeck login SMS (validate phone → auth/login).”

  3 inputs, 1 required

  • step_2_body_phonestringrequired“User-provided phone without country prefix (local NG format like 080…).”
  • step_2_body_country_codestring“Country code (e.g.”
  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• verify_login_otp

  “Complete ChowDeck login with SMS code (validate phone → validate OTP → refresh token).”

  4 inputs, 2 required

  • step_2_body_phonestringrequired“Same phone used in request_login_otp”
  • step_2_body_country_codestring“Country code (e.g.”
  • step_5_body_otpstringrequired“SMS one-time code from the user”
  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• fetch_customer_settings

  “Public customer app config (no auth).”

  1 input

  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• view_carton 6 other servers

  “View current cart contents.”

  1 input

  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• get_addresseson 1 other server

  “Run the get_addresses pipeline.”

  1 input

  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• get_payment_methodson 7 other servers

  “Run the get_payment_methods pipeline.”

  1 input

  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• list_orders_success

  “Run the list_orders_success pipeline.”

  1 input

  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• get_order_detailson 3 other servers

  “Run the get_order_details pipeline.”

  1 input

  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• get_customer_survey

  “Run the get_customer_survey pipeline.”

  1 input

  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• set_active_address_and_fetch_menu

  “Set active delivery address and fetch chowsmart menu for that address.”

  4 inputs, 2 required

  • step_37_body_address_idstringrequired“Address id to set as active (from get_addresses)”
  • step_37_body_addressIdstring“Same address id (duplicate field in API body)”
  • step_38_url_query_address_idstringrequired“Same address id for menu fetch”
  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• get_featured_vendors

  “Featured and tagged vendors near a delivery address.”

  4 inputs, 1 required

  • step_40_url_query_address_idstringrequired“Active delivery address id (from get_addresses or set_active_address)”
  • step_40_pageinteger“Page number for featured vendors (default 1).”
  • step_40_page_sizeinteger“Vendors per page (default 25, max 100)”
  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”
• get_chowpass_status

  “Run the get_chowpass_status pipeline.”

  1 input

  • notification_messagestring“Short user-facing sentence for this action if the follow-up reply fails.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-02.

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.