mcp-connector
Enables read-only interaction with TallyPrime accounting data, letting users ask accounting questions and retrieve live company information, financial reports, and ledgers without altering anything in Tally.
README
mcp-connector
Read-only TallyPrime MCP. Cursor asks accounting questions; this server fetches live company data over Tally XML Export. Nothing is created, altered, or deleted in Tally.
Flow:
Cursor → Streamable HTTP MCP → Node → TallyPrime
Setup
Copy .env.example to .env next to tally.js and server.js:
TALLY_URL=http://192.168.29.149:9000
HOST=0.0.0.0
PORT=3000
TALLY_URL is the TallyPrime HTTP port on the Tally PC (9000). Do not expose that port to the internet.
npm install
node server.js
Health: GET http://127.0.0.1:3000/health
MCP: POST http://127.0.0.1:3000/mcp
STDIO (optional): node server.js --stdio
Tally connectivity check: node test-tally.js
Remote Cursor
On another PC on the LAN, add this MCP server (this machine’s LAN IP is 192.168.29.47):
{
"mcpServers": {
"tally": {
"url": "http://192.168.29.47:3000/mcp"
}
}
}
Allow inbound TCP 3000 on this PC. Keep Tally port 9000 local.
Tools
Four tools, not one per report:
| Tool | Purpose |
|---|---|
query_tally |
Companies, ledgers, groups, customers, suppliers, cash, bank, stock, GST, vouchers, outstanding |
tally_report |
Profit & loss, balance sheet, trial balance, registers, GST and stock reports |
tally_describe |
Catalog of resources, filters, and example questions |
get_ledgers |
Original smoke test: Tally Collection List of Ledgers, raw XML |
Dates should match the loaded Tally financial year. Pass financialYear such as 26-27, or explicit fromDate / toDate as YYYY-MM-DD.
Layout
mcp-connector/
.env
tally.js Tally HTTP client (Export POST)
server.js Streamable HTTP MCP
test-tally.js Connectivity check
lib/
mcp-server.js Tool registration
query.js Read-only query layer
catalog.js Resources and reports
dates.js Dates and Indian FY
parse.js Tally XML → JSON
xml-build.js Read-only Export XML
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.