TaxbyKK GST Research

TaxByKK is a GST document intelligence service that connects to Claude and ChatGPT through MCP.

CommunityOnlineNo 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.

How to connect

How to connect TaxbyKK GST Research to Claude

The server address to paste into Claude settings:

https://a2432143-_fjdiafd3j432--anirudhagrawal6778.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect TaxbyKK GST Research to ChatGPT

The server address to paste into ChatGPT settings:

https://a2432143-_fjdiafd3j432--anirudhagrawal6778.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect TaxbyKK GST Research to Cursor

The server address to paste into Cursor settings:

https://a2432143-_fjdiafd3j432--anirudhagrawal6778.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (8)

Raw names from tools/list. Only developers need these.

subscription_statusReturn the current TaxByKK access and subscription status, including links to subscribe or manage billing.
open_taxbykk_prompt_galleryOpen the interactive TaxByKK prompt gallery when the user asks to browse, view, or choose a TaxByKK prompt.
list_documentsList 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_documentsPrimary 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_structureGet 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_textPage-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_pagesRead 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_imageRetrieve 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.