IndiaMART MCP Server
Enables managing IndiaMART buyer leads through natural language, including fetching, searching, analyzing, and updating lead pipeline stages.
README
🇮🇳 IndiaMART MCP Server
<!-- mcp-name: io.github.Techmatic-sys/indiamart-mcp-server -->
A fully functional Model Context Protocol (MCP) server that connects Claude AI to IndiaMART's Lead Management API. Fetch, search, analyze, and manage your IndiaMART buyer leads using natural language.
⚡ Quick Install (60 seconds)
git clone https://github.com/Techmatic-sys/indiamart-mcp-server.git
cd indiamart-mcp-server
pip install -r requirements.txt
Then add to your Claude Desktop config and you're done. Full setup below.
✨ Features
- 10 MCP Tools — 8 read tools + 2 write tools for complete CRM
- Pull Leads — Fetch leads from IndiaMART for any date range
- Pipeline Management — Track leads through sales stages (new → won)
- Notes — Attach private notes to leads for context
- Real-time Webhook — Receive leads instantly via IndiaMART's Push API
- Local Database — All leads stored in SQLite for fast offline access
- Analytics — Get stats by city, product, and date
- Search — Find leads by keyword in product or message
- Export CSV — Export leads for spreadsheets and reporting
- Draft Replies — Generate professional buyer replies instantly
- Input Validation — Pydantic schemas prevent malformed queries
- Retry Logic — Exponential backoff on API failures
- Claude Desktop Ready — Plug-and-play config included
📋 Prerequisites
- Python 3.10+ (Download)
- IndiaMART Seller Account with Lead Manager access
- IndiaMART CRM API Key (see below)
- Claude Desktop (optional, for AI-powered lead management)
🚀 Installation
1. Clone or Download
git clone https://github.com/Techmatic-sys/indiamart-mcp-server.git
cd indiamart-mcp-server
2. Create Virtual Environment (recommended)
python -m venv venv
# Windows
venv\Scripts\activate
# macOS/Linux
source venv/bin/activate
3. Install Dependencies
# MCP server only (lightweight, 4 packages)
pip install -r requirements.txt
# Full SaaS web app (includes FastAPI, uvicorn, etc.)
pip install -r requirements-saas.txt
4. Configure Environment
# Copy the example env file
cp .env.example .env # Linux/macOS
copy .env.example .env # Windows
# Edit .env with your credentials
🔑 How to Get Your IndiaMART API Key
- Log in to IndiaMART Seller Dashboard
- Go to Lead Manager → Settings (⚙️ icon)
- Navigate to CRM Integration or API Settings
- Generate or copy your CRM API Key (
glusr_crm_key) - Note your GLID (Global Login ID) from your account profile
- Paste both values into your
.envfile
Note: The API key gives access to your leads. Keep it secret!
▶️ Running the MCP Server
# Standard run (Claude Desktop starts this automatically)
python mcp_server.py
# Check version
python mcp_server.py --version
# Health check (verify DB connectivity)
python mcp_server.py --health
🖥️ Connecting to Claude Desktop
1. Locate Claude Desktop Config
| OS | Path |
|---|---|
| Windows | %APPDATA%\Claude\claude_desktop_config.json |
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Linux | ~/.config/Claude/claude_desktop_config.json |
2. Add the MCP Server
{
"mcpServers": {
"indiamart": {
"command": "python",
"args": ["mcp_server.py"],
"cwd": "/ABSOLUTE/PATH/TO/indiamart-mcp-server",
"env": {
"INDIAMART_API_KEY": "your_crm_api_key_here",
"INDIAMART_GLID": "your_glid_here"
}
}
}
}
Replace cwd with your actual path:
- Windows:
"C:\\Users\\YourName\\indiamart-mcp-server" - macOS:
"/Users/yourname/indiamart-mcp-server" - Linux:
"/home/yourname/indiamart-mcp-server"
3. Restart Claude Desktop
Close and reopen Claude Desktop. You should see the IndiaMART tools available in the tools menu.
🤖 Connecting to Claude Code
Option 1: CLI (Recommended)
claude mcp add indiamart -- python /ABSOLUTE/PATH/TO/indiamart-mcp-server/mcp_server.py
Then set your environment variables:
# In your shell profile or before launching Claude Code
export INDIAMART_API_KEY="your_crm_api_key_here"
export INDIAMART_GLID="your_glid_here"
Option 2: Manual Config
Add to your .claude/settings.json (project-level) or ~/.claude/settings.json (global):
{
"mcpServers": {
"indiamart": {
"command": "python",
"args": ["/ABSOLUTE/PATH/TO/indiamart-mcp-server/mcp_server.py"],
"env": {
"INDIAMART_API_KEY": "your_crm_api_key_here",
"INDIAMART_GLID": "your_glid_here"
}
}
}
}
Replace the path with your actual absolute path to mcp_server.py.
Verify Connection
Once connected, ask Claude Code:
- "Sync my latest IndiaMART leads"
- "Show me leads from the last 24 hours"
- "What are my lead statistics?"
🦞 Connecting to OpenClaw
OpenClaw is a self-hosted AI agent platform. Your IndiaMART leads become a native skill in OpenClaw, accessible from any interface OpenClaw supports.
1. Find your OpenClaw config file
| OS | Path |
|---|---|
| Linux/macOS | ~/.openclaw/openclaw.json |
| Windows | C:\Users\YourName\.openclaw\openclaw.json |
2. Add the IndiaMART skill
Open the config and add under skills.mcpServers:
{
skills: {
mcpServers: {
indiamart: {
command: "python",
args: ["mcp_server.py"],
cwd: "/absolute/path/to/indiamart-mcp-server",
env: {
INDIAMART_API_KEY: "your_crm_api_key_here",
INDIAMART_GLID: "your_glid_here"
}
}
}
}
}
See
openclaw-config-example.json5at the repo root for a ready-to-copy template.
3. Restart the OpenClaw gateway
openclaw gateway restart
4. Verify it loaded
openclaw status --all
# You should see "indiamart" listed with 10 tools
Remote OpenClaw (VPS / EC2)
Run the MCP server in SSE mode on your server:
python mcp_server.py --transport sse --host 0.0.0.0 --port 8000
Then point your OpenClaw config to http://your-server-ip:8000.
💬 Example Prompts
| Prompt | What It Does |
|---|---|
| "Show me all leads from the last 24 hours" | Syncs and displays recent leads |
| "How many leads did I get this week and from which cities?" | Shows lead statistics |
| "Search for leads asking about steel pipes" | Keyword search in product/message |
| "Draft a reply for lead ID IML123456789" | Generates professional buyer reply |
| "Move lead IML123 to qualified stage" | Updates pipeline stage |
| "Add a note to lead IML123: Very interested in bulk order" | Attaches a note |
| "Export all leads from January 2026 as CSV" | Exports leads in CSV format |
| "Sync my latest IndiaMART leads" | Pulls latest leads into local DB |
🛠️ Available MCP Tools (10 Total)
Read Tools (8)
| Tool | Description |
|---|---|
tool_get_leads_by_date |
Fetch leads from IndiaMART for a date range |
tool_get_recent_leads |
Get leads from the last N hours |
tool_get_lead_stats |
Analytics: totals, by city, product, and date |
tool_search_leads |
Search leads by keyword |
tool_get_lead_by_id |
Full details of a specific lead |
tool_draft_reply |
Draft a professional reply for a buyer |
tool_export_leads_csv |
Export leads as CSV |
tool_sync_latest_leads |
Sync latest from IndiaMART to local DB |
Write Tools (2 — NEW)
| Tool | Description |
|---|---|
tool_update_lead_stage |
Move leads through pipeline (new → contacted → qualified → won/lost) |
tool_add_note |
Attach private notes to leads for follow-up tracking |
📁 Project Structure
indiamart-mcp-server/
├── 📄 mcp_server.py ← SINGLE entry point
├── 📄 smithery.yaml ← Smithery.ai marketplace manifest
├── 📄 pyproject.toml ← Python package config
├── 📄 requirements.txt ← MCP only (5 packages)
├── 📄 requirements-saas.txt ← Web app deps
├── 📄 README.md ← This file
├── 📄 CHANGELOG.md ← Version history
├── 📄 LICENSE ← MIT License
├── 📄 .env.example ← Annotated credential guide
├── 📄 .gitignore ← Git ignore rules
├── 📄 docker-compose.yml ← Full stack Docker setup
│
├── 📁 mcp_tools/ ← Core MCP Package
│ ├── __init__.py
│ ├── 🔧 tools.py ← 10 MCP tools with rich docstrings
│ ├── 📋 schemas.py ← Pydantic validation + response types
│ ├── 🌐 http_client.py ← Resilient API client with retry
│ ├── 💾 database.py ← SQLite operations
│ ├── 🔑 auth.py ← API key helpers
│ └── 🐳 Dockerfile ← MCP server Docker image
│
├── 📁 saas/ ← SaaS Web App (FastAPI)
│ └── ...
│
├── 📁 tests/ ← Test suite
│ ├── conftest.py ← pytest fixtures
│ └── test_tools.py ← Validation + integration tests
│
├── 📁 .github/ ← CI/CD
│ └── workflows/ci.yml
│
└── 📁 docs/ ← Documentation
├── tools.md
└── examples.md
🔧 Troubleshooting
"INDIAMART_API_KEY is not set"
- Make sure you've created a
.envfile (not just.env.example) - Check that the key is correct and not expired
- Verify the
.envfile is in the project root directory
Claude Desktop doesn't show IndiaMART tools
- Restart Claude Desktop completely (quit + reopen)
- Check
claude_desktop_config.jsonfor syntax errors (valid JSON?) - Verify the
cwdpath is correct andmcp_server.pyexists there - Check Claude Desktop logs for MCP connection errors
Date format errors
- Supported formats:
YYYY-MM-DD,DD-MM-YYYY,DD/MM/YYYY,DD-Mon-YYYY - Example:
2026-01-15,15-01-2026,15-Jan-2026
📄 License
MIT License. Use freely for your business.
🤝 Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/my-feature - Commit changes:
git commit -m "Add my feature" - Push:
git push origin feature/my-feature - Open a Pull Request
Built with ❤️ for Indian sellers on IndiaMART
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。