Dhan Broker MCP Trades

Created By
mayanktholea year ago
Dhan Trading MCP Server A Model Context Protocol (MCP) server integration for the Dhan Trading API, allowing Claude to access your trading account information. Overview This project creates an MCP server that connects the Dhan Trading API with Claude AI, enabling Claude to: Check your account balance View your holdings and positions Get live profit and loss information Fetch latest trading prices Place and manage orders Installation Prerequisites Python 3.8+ installed Claude Desktop application Dhan Trading account with API credentials
Overview

Dhan-Claude MCP Integration: Project Overview What We Built We've created a Model Context Protocol (MCP) server that connects Claude AI to the Dhan Trading platform. This integration allows Claude to directly access your Dhan trading account data and perform actions like checking balances, viewing positions, and fetching market prices. Key Components

  1. MCP Server At the core of our implementation is a Python-based MCP server that acts as a bridge between Claude and the Dhan API. This server:

Exposes Dhan account data as structured resources Provides tools for Claude to fetch real-time market information Handles the communication protocol between Claude and Dhan

  1. Integration Points Our integration connects to two main systems:

Dhan Trading API: Accesses your financial data through the Dhan-Tradehull package Claude Desktop: Connects via the Model Context Protocol to enable Claude to use your trading data

  1. Available Functionality The integration enables Claude to:

Check your account balance View your current holdings and positions Monitor live profit and loss (P&L) Get latest trading prices for symbols View option chain data (in extended implementation)

Technical Architecture The system follows a clean architecture pattern:

Client Layer: Claude Desktop acts as the client Protocol Layer: MCP manages the standardized communication API Integration Layer: Connects to Dhan's trading API Security Layer: Credentials are stored as environment variables

Implementation Approach We started with a simple approach to ensure connectivity:

Built a basic echo server to test MCP connectivity Added Dhan API integration for account information Handled special output redirection to prevent protocol issues Configured the server to work with Claude Desktop

Security Considerations The implementation keeps your trading credentials secure by:

Using environment variables instead of hardcoded credentials Running locally on your machine without exposing data to external servers Only accessing the specific Dhan API endpoints needed for functionality

Benefits This integration delivers several advantages:

Conversational Interface: Access your trading data by simply chatting with Claude Contextual Awareness: Claude can reference your portfolio when providing insights Seamless Experience: No need to switch between applications to check your investments Extensibility: The framework allows for adding new capabilities in the future

Next Steps The current implementation provides foundational functionality, but could be extended to include:

Trade execution capabilities Portfolio analysis and visualization Automated alerts based on market conditions Historical performance tracking

Server Config

{
  "mcpServers": {
    "after-market-order": {
      "command": "/Library/Frameworks/Python.framework/Versions/3.13/bin/python3",
      "args": [
        "/Users/mayankthole/Desktop/Dhan Broker MCP trades/after_market_order_tool.py"
      ]
    },
    "fund-balance": {
      "command": "/Library/Frameworks/Python.framework/Versions/3.13/bin/python3",
      "args": [
        "/Users/mayankthole/Desktop/Dhan Broker MCP trades/fund_balance_tool.py"
      ]
    },
    "holdings-positions": {
      "command": "/Library/Frameworks/Python.framework/Versions/3.13/bin/python3",
      "args": [
        "/Users/mayankthole/Desktop/Dhan Broker MCP trades/holdings_positions_tool.py"
      ]
    },
    "margin-calculator": {
      "command": "/Library/Frameworks/Python.framework/Versions/3.13/bin/python3",
      "args": [
        "/Users/mayankthole/Desktop/Dhan Broker MCP trades/margin_calculator_tool.py"
      ]
    },
    "order-book": {
      "command": "/Library/Frameworks/Python.framework/Versions/3.13/bin/python3",
      "args": [
        "/Users/mayankthole/Desktop/Dhan Broker MCP trades/order_book_tool.py"
      ]
    },
    "order-placement": {
      "command": "/Library/Frameworks/Python.framework/Versions/3.13/bin/python3",
      "args": [
        "/Users/mayankthole/Desktop/Dhan Broker MCP trades/order_placement_tool.py"
      ]
    },
    "portfolio-server": {
      "command": "/Library/Frameworks/Python.framework/Versions/3.13/bin/python3",
      "args": [
        "/Users/mayankthole/Desktop/Dhan Broker MCP trades/portfolio_server.py"
      ]
    },
    "super-order": {
      "command": "/Library/Frameworks/Python.framework/Versions/3.13/bin/python3",
      "args": [
        "/Users/mayankthole/Desktop/Dhan Broker MCP trades/super-order.py"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
mayankthole
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

a day ago
Linkpulse

a day ago
Trainzilla Mcp

8 hours ago