Tally Prime MCP Server

Tally Prime MCP (Model Context Protocol) Server implementation to feed Tally Prime ERP data to popular LLM like Claude, ChatGPT supporting MCP client. This MCP Server helps expose functionalities of Tally to LLM directly.

Prerequisites

Tally Prime (Silver / Gold) Node JS

Ensure below things are pre-installed and setup:
Ensure to download & install Node JS from official website
XML Port of Tally Prime must be enabled (F1 > Settings > Connectivity > Client/Server configuration) with below settings

TallyPrime acts as = Server

Port = 9000

Note: Kindly avoid using Educational version of Tally Prime, which has limitations of date range. It will result in invalid / partial data being fed to LLM, leading to highly degraded & incorrect responses.

Download

Avoid cloning repository directly. Utility is available for download (with required dependencies) on below link <br> https://excelkida.com/resource/tally-mcp-server-v7.4.zip

One-click installer extension for Claude Desktop<br>
https://excelkida.com/resource/tally-mcp-server-v7.4.mcpb

Last updated: version 7.4 [03-Jul-2026]

Refer docs/CHANGELOG.md for details

Supported Platform

Implementation was tested on below AI platform

|Platform|Local|Remote|
|--|--|--|
|Claude AI| :heavy_check_mark: | :heavy_check_mark: |
|ChatGPT|| :heavy_check_mark: |

Setup (Local)

This mode of setup is to be used when MCP Client (like Claude Desktop, Perplexity etc.) and Tally Prime both exists in local PC. MCP Client software itself runs the MCP Server internally in such scenario.

Simply download &amp; extract zip file somewhere on the disk. Assuming that we downloaded &amp; extracted zip file on below path (folder)

D:\Software\Tally MCP Server

<image src="https://excelkida.com/image/github/explorer-tally-mcp-server.png" height="265" width="766" />

A sample setup for few popular tools is demonstrated.

Claude Desktop

Desktop version of Claude AI supports loading of local MCP server. Ensure you have Pro / Team / Max / Enterprise subscription of Claude, which supports higher limit compared to Free. MCP makes multiple calls to Tally for validation and inference, which might exhaust free limits quickly. Download Claude Desktop from following link claude.ai/download

One-click installation (via Extension)

Go to menu &gt; File &gt; Settings

<image src="https://excelkida.com/image/github/claude-desktop-settings-menu.png" height="185" width="335">

Extensions &gt; Advance Settings

<image src="https://excelkida.com/image/github/claude-desktop-settings-extension.png" height="553" width="928">

Click on install extension button

<image src="https://excelkida.com/image/github/claude-desktop-extension-page.png" height="619" width="868">

Browse the extension file (with file extension mcpb) download at the start

<image src="https://excelkida.com/image/github/claude-desktop-extension-install.png" height="843" width="696">

A dialog window will appear asking Do you want to install Tally Prime? click Install button, which would install the Tally MCP Server

Installation via Config file (via Developer menu)

Go to menu &gt; File &gt; Settings &gt; Developer

<image src="https://excelkida.com/image/github/claude-desktop-developer-setting.png" height="751" width="1045" />

This will open My Computer window. Right click and edit claude_desktop_config.json file (via Notepad) with as below JSON

{

  "mcpServers": {

	  "Tally Prime": {

		  "command": "node",

		  "args": ["D:\\Software\\Tally MCP Server\\dist\\index.mjs"]

	  }

  }

}

Note: single slash in folder path needs to be substituted with double slash

Save the file. Close Claude Desktop (menu &gt; File &gt; Exit) and again re-launch it.

Verify by clicking on Tools button and check if Tally Prime appears in the list (screenshot below)

<image src="https://excelkida.com/image/github/claude-desktop-tally-mcp-server-tool-display.png" height="595" width="722" />

Perplexity Desktop

Perplexity Desktop version for MacOS supports connecting to local MCP server. Configuration file (JSON format) is same as demonstrated for Claude Desktop. In absense of MacBook, documentation with screenshot could not be written. Kindly refer to below blog on perplexity website, which explains the steps.

Perplexity Desktop MCP Connectivity

Setup (Cloud)

This mode of setup is to be used, when using browser-based MCP client like ChatGPT, Claude AI, Copilot, OR mobile-based app for these LLM which cannot access Tally Prime running inside local PC. In this scenario, MCP Server needs to run as web-server, internally connected to Tally securely. Setup is quite complicated, and is covered in detail in docs folder of this project. Linux-based Server Windows Server (exploration in-progress)

Available Tools

This server currently exposes 19 MCP tools.

metadata-collection

Returns metadata for supported collections.

Input
No input.

Output
JSON array with objects containing:
1. collection
1. description

query-option-values

Returns predefined option values used by input fields.

Input
|Argument|Description|
|--|--|
|optionName|Supported: country-state|

Output
JSON array of option values for the selected option name.

metadata-fields

Returns field metadata for a selected collection.

Input
|Argument|Description|
|--|--|
|collection|Collection name. Use metadata-collection to discover valid values|

Output
JSON array of field metadata containing field name, description (if any), and normalized datatype (string, number, date, boolean).

query-database

Runs SQL query on in-memory pglite tables previously created by reporting tools.

Input
|Argument|Description|
|--|--|
|sql|SELECT query only|
|outputFormat|One of JSON Array of Objects, JSON with Schema and Rows, CSV, Markdown Table. Default is JSON Array of Objects which is preferred format|

Output
Query result in tab-separated text format.

query-collection

Queries a Tally collection for selected fields and caches output in an in-memory table.

Input
|Argument|Description|
|--|--|
|collection|Collection name|
|fields|Array of field names to fetch|
|targetCompany (optional)|Company name (defaults to active company)|
|fromDate (optional)|Date in YYYY-MM-DD|
|toDate (optional)|Date in YYYY-MM-DD|

Output
JSON: { "tableID": "..." }

list-master

Fetches list of masters for validation and auto-completion.

Input
|Argument|Description|
|--|--|
|targetCompany (optional)|Company name (defaults to active company)|
|collection|One of: group, ledger, vouchertype, unit, godown, stockgroup, stockitem, costcategory, costcentre, attendancetype, company, currency, gstin, gstclassification|
|containsFilter (optional)|filter to apply CONTAINS operation to restrict values|

Output
JSON: { "list": [ ... ] }

chart-of-accounts

Extracts Chart of Accounts (or Group hierarchy) useful for preparing Balance Sheet, Profit and Loss, Trial Balance

Input
|Argument|Description|
|--|--|
|targetCompany (optional)|Company name (defaults to active company)|

Output
JSON: { "tableID": "..." } with columns:
1. ledger_name
1. group_name
1. primary_group
1. bs_pl (boolean) [true = Profit &amp; Loss / false = Balance Sheet]
1. dr_cr (boolean) [true = Debit / false = Credit]
1. affects_gross_profit (boolean) [true = Affects Gross Profit / false = Does not affect Gross Profit]
1. sort_position (number)

trial-balance

Fetches trial balance for period.

…