TaxbyKK GST Research
TaxByKK is a GST document intelligence service that connects to Claude and ChatGPT through MCP.
Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only
What it can do
- Subscription Status: Return the current TaxByKK access and subscription status, including links to subscribe or manage billing.
- Open Taxbykk Prompt Gallery: Open the interactive TaxByKK prompt gallery when the user asks to browse, view, or choose a TaxByKK prompt.
- List Documents: List all documents available in the user's TaxByKK document library. Use this when the user asks what documents, PDFs, papers, files, or uploads are available. A document's canonical s
What data it sees
Do you need an account
No: the server works without sign-in
TaxByKK is a GST document intelligence service that connects to Claude and ChatGPT through MCP. It helps the assistant search the connected tax library, read relevant pages and return answers with source references.
Server tool list (8)
Raw names from tools/list. Only developers need these.
| subscription_status | Return the current TaxByKK access and subscription status, including links to subscribe or manage billing. |
| open_taxbykk_prompt_gallery | Open the interactive TaxByKK prompt gallery when the user asks to browse, view, or choose a TaxByKK prompt. |
| list_documents | List all documents available in the user's TaxByKK document library. Use this when the user asks what documents, PDFs, papers, files, or uploads are available. A document's canonical source URL is the first line of its page 1, so when the user asks for a document's link or source, call read_pages on page 1 to retrieve it. |
| find_relevant_documents | Primary semantic document discovery using TaxByKK. Use this first for conceptual, topic-based, or natural-language questions over uploaded PDFs, especially when the query does not contain exact legal identifiers. Examples: composite supply of battery with inverter, GST exemption for hostel accommodation, taxability of vouchers, input tax credit eligibility. This returns document candidates only, not answer chunks. After semantic candidates are found, use search_document_text with a short key phrase or read_pages to locate exact page evidence. For legal, tax, regulatory, statutory, or compliance questions, follow material cross-references found in candidate documents, including connected sections, rules, sub-rules, forms, circulars, notifications, advisories, amendment notes, and effective dates. A document's canonical source URL is the first line of its page 1, so when the user asks for a document's link or source, call read_pages on page 1 to retrieve it. |
| get_document_structure | Get the hierarchical TaxByKK outline/tree for a selected document. Use document_id exactly as returned by find_relevant_documents or list_documents. Use this before reading pages. For legal/tax/regulatory questions, inspect the outline for nearby legislative-history, commentary, amendment, circular, notification, rule, or connected-provision sections that may affect the answer. |
| search_document_text | Page-level full-text search over indexed TaxByKK document text. Use this first for exact anchors such as section numbers, rule numbers, sub-rule numbers, forms, appeal numbers, case numbers, writ petition numbers, notification numbers, circular numbers, order/ruling numbers, citations, exact dates tied to legal references, quoted phrases, or exact document references. For conceptual or topic-based queries without exact anchors, first call find_relevant_documents with the full query, then use this tool with a short key phrase to locate page-level evidence. For legal/tax/regulatory questions, also use this after read_pages whenever retrieved text mentions material connected provisions or authorities such as 'section 37', 'rule 60(7)', 'sub-rule (7) of rule 60', 'Circular No.', 'Notification No.', 'FORM GSTR-2B', 'w.e.f.', 'inserted', 'substituted', or 'omitted'. When following cross-references, search each material anchor separately with short queries; do not combine a rule number, sub-rule, form, circular, and topic into one long query because relevant pages may use different wording. Returns matching document_id, title, and page_number. |
| read_pages | Read exact page content from a selected document. Use document_id exactly as returned by find_relevant_documents, search_document_text, or list_documents. Use tight page ranges like '5', '3,7,10', or '5-10'. For legal/tax/regulatory questions, treat this as an evidence-gathering step: if the pages mention connected sections, rules, sub-rules, forms, circulars, notifications, advisories, amendment notes, or effective dates, call search_document_text for those material anchors and read the connected pages before answering. If the answer depends on figures, charts, diagrams, tables, or visual details, inspect image annotations and call get_image. The first line of page 1 is the document's canonical source URL; surface it when the user asks for the document's link. |
| get_image | Retrieve an image, chart, diagram, figure, or visual table from TaxByKK using an imagePath returned by read_pages. Use this when the page text is incomplete or the question depends on visual evidence. |