tally-mcp-server
This MCP server exposes TallyPrime/Tally.ERP 9 accounting and inventory data to MCP-compatible clients.
List Companies – Retrieve all companies available in the connected Tally instance.
List Ledgers – Fetch all ledger accounts with opening and closing balances.
List Groups – Get accounting groups (chart-of-accounts categories) like Sundry Debtors, Bank Accounts, Direct Expenses.
List Stock Items – Retrieve inventory stock items with closing quantity, rate, and value.
Day Book – Query vouchers (sales, purchases, receipts, payments, journals) posted between two dates (format: YYYYMMDD).
Outstanding Balances – Fetch ledgers within a specific group (default: Sundry Debtors for receivables; change to Sundry Creditors for payables) with current closing balances.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tally-mcp-server Show outstanding balances for all customer ledgers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tally-mcp-server
An MCP (Model Context Protocol) server that exposes TallyPrime data to any MCP-compatible client (Claude Desktop, Claude Code, etc.) over Tally's classic XML HTTP API - the integration method supported by every Tally.ERP 9 / TallyPrime release.
Available tools
Tool key | What it returns |
| Companies known to the running Tally instance |
| All ledger accounts, with opening/closing balances |
| All accounting groups (chart-of-accounts categories) |
| All inventory items, with closing qty/rate/value |
| Vouchers posted between two dates ( |
| Ledgers in a group with closing balance (receivables/payables) |
Related MCP server: Tally MCP Server
How it talks to Tally
TallyPrime can act as an HTTP server and accept an XML "envelope":
<ENVELOPE><HEADER>...</HEADER><BODY>...</BODY></ENVELOPE>. Two request
shapes are used here:
Built-in reports (e.g.
list_companies) - just name the report, no TDL needed.Custom collections (everything else) - an inline TDL
<COLLECTION>naming a native Tally object type (Ledger,Group,StockItem,Voucher) and the fields to fetch. This is the standard technique for "give me all X" pulls and is what most third-party Tally integrations use.
Docs: https://help.tallysolutions.com/developer-reference/introduction/integration-with-tallyprime/
1. Enable Tally as an HTTP server
In TallyPrime: F1 (Help) → Settings → Connectivity → Client/Server
configuration → set "TallyPrime acts as" to Server, and note the port
(default 9000).
2. Install
npm install
cp .env.example .env
# edit .env if your Tally isn't on localhost:90003. Run standalone (for testing)
npm startThe server speaks MCP over stdio, so running it directly won't print
anything to stdout - that's expected. Ctrl+C to stop.
4. Connect it to an MCP client
Example Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"tally": {
"command": "node",
"args": ["/absolute/path/to/tally-mcp-server/src/index.js"]
}
}
}Project structure
src/
├── index.js # MCP server bootstrap - wires everything together
├── config.js # Reads TALLY_HOST / TALLY_PORT / etc. from .env
├── tally/
│ ├── client.js # Generic transport: builds/sends the XML envelope,
│ │ # parses the XML response into a plain object
│ └── endpoints/
│ ├── index.js # Registry - list every supported Tally API here
│ ├── companies.js # Built-in report example
│ ├── ledgers.js # Custom TDL collection example
│ ├── groups.js
│ ├── stockItems.js
│ ├── dayBook.js # Collection example with runtime params (dates)
│ └── outstanding.js # Collection example with a filter
└── tools/
└── index.js # Turns every registered endpoint into an MCP toolThe split matters:
tally/client.jsonly knows how to transport a request (build the XML envelope, POST it, parse the XML response, surface errors). It has zero Tally-report-specific knowledge.tally/endpoints/*.jseach describe one Tally API: what to request (request: { kind, ... }), any input parameters it needs, and how to turn Tally's parsed XML into a clean shape.tools/index.jsloops over the endpoint registry and callsserver.tool(...)for each one - so a new endpoint becomes a working MCP tool automatically, with no changes to the server or client code.
Adding a new Tally API
Say you want to add "List Cost Centres":
Create
src/tally/endpoints/costCentres.js, modeled ongroups.js:import { asArray } from "../client.js"; export default { key: "list_cost_centres", title: "List Cost Centres", description: "Returns cost centres from TallyPrime.", inputSchema: {}, request: { kind: "collection", collectionName: "MCP CostCentres", type: "CostCentre", fetch: ["NAME", "PARENT", "CATEGORY"], }, parseResponse(parsedXml) { const entries = asArray(parsedXml?.ENVELOPE?.COSTCENTRE); return entries.map((e) => ({ name: e["@_NAME"] ?? e.NAME, parent: e.PARENT, category: e.CATEGORY, })); }, };Register it in
src/tally/endpoints/index.js(import + add to theendpointsarray).Restart the server.
list_cost_centresis now a callable MCP tool - nothing else needs to change.
If an endpoint needs runtime parameters (dates, a filter value, etc.),
add zod validators to inputSchema and read them in request.staticVariables(params)
and/or request.buildFilterValue(params) - see dayBook.js and
outstanding.js for examples.
Troubleshooting
"Could not reach TallyPrime" - Tally isn't running, isn't configured as a server, or
TALLY_HOST/TALLY_PORTin.envdon't match.Empty results or
<LINEERROR>- the report/collectionidor TDL field names may need adjusting for your Tally release or company configuration. Turn on Tally's "Test Client" / check the Tally log screen while a request runs to see exactly what it received.Unexpected shape in
list_companies-parseResponse()tries a few likely XML shapes and falls back to returning the raw parsed payload with awarningfield so you can see exactly what Tally sent back and adjust the parser.Numbers coming back as strings/numbers inconsistently - Tally's XML doesn't strongly type values;
fast-xml-parserdoes its best guess. If you need guaranteed types, cast explicitly insideparseResponse().
To test MCP sever in browser
npx @modelcontextprotocol/inspector node src/index.jsAvailable Tools
6 toolsday_bookA
Returns all vouchers (sales, purchases, receipts, payments, journals, etc.) posted in TallyPrime between two dates.
Inputs: toDate (required), fromDate (required).
list_companiesA
Returns the list of companies available in the connected TallyPrime instance.
Inputs: no named parameters.
list_groupsA
Returns all accounting groups (chart-of-accounts categories) from TallyPrime, e.g. Sundry Debtors, Bank Accounts, Direct Expenses.
Inputs: no named parameters.
list_ledgersA
Returns all ledger accounts (parties, banks, cash, expense/income heads, etc.) from TallyPrime, with opening and closing balances.
Inputs: no named parameters.
list_stock_itemsA
Returns all inventory stock items from TallyPrime with closing quantity, rate, and value.
Inputs: no named parameters.
outstanding_balancesA
Returns ledgers in a given account group (default: Sundry Debtors, i.e. receivables) with their current closing balance. Pass group: 'Sundry Creditors' for payables.
Inputs: group.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct Tally entity: companies, ledgers, groups, stock items, vouchers, and balance status. There is no overlap in the data returned, so an agent can easily select the right tool.
Most tools follow a list_* pattern (list_companies, list_ledgers, list_groups, list_stock_items), but day_book and outstanding_balances deviate. Despite this, the names remain descriptive and predictable.
Six tools is a well-scoped set for a TallyPrime integration, covering the primary read operations without being sparse or overwhelming.
The tool set provides comprehensive read-only coverage of accounting entities: masters, transactions, and balances. Minor gaps exist, such as no voucher-level detail beyond day_book, but the core reporting needs are met.
Related MCP Connectors
AI for Tally Prime and Tally ERP 9. Hosted MCP server to ask your accounts in any language.
Headless API-first double-entry accounting & bookkeeping engine. 84 MCP tools over HTTP.
MCP server for Codat — companies, connections, invoices, bills and financial statements.
Provide seamless access to Appfolio Property Manager Reporting API through a standardized MCP serv…
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceConnects Tally Prime ERP data to AI assistants via MCP, enabling natural language queries for financial reports, stock summaries, and ledger balances.MIT
- AlicenseAqualityCmaintenanceAn MCP server that lets Claude read from and write to TallyPrime via its built-in XML/HTTP gateway.233ISC
- AlicenseAqualityBmaintenanceThis MCP server enables users to read from and write to TallyPrime via its XML/HTTP gateway, supporting operations like ledger management, voucher creation, and financial report retrieval through natural language.873ISC
- AlicenseNot gradedqualityBmaintenanceEnables LLMs like Claude and ChatGPT to access and interact with Tally Prime ERP data through MCP, including financial reports, ledgers, trial balance, balance sheet, profit and loss, and stock summary.AGPL 3.0