Amazon & Flipkart MCP Server
Lightweight MCP server for interacting with Amazon and Flipkart search and authentication components.
README
Amazon & Flipkart MCP Server
Lightweight MCP (Marketplace Content Proxy) server and tools for interacting with Amazon and Flipkart search/auth components. This repository contains a small service, utilities, and tests used during development.
Repository layout
main.py— top-level entry (project wrapper).pyproject.toml— top-level packaging metadata.amazon_flipkart_mcp(1)/amazon_flipkart_mcp/— primary package directory containing the service and modules:config.py— configuration and settings.server.py— MCP server entrypoint (HTTP/service glue).main.py— package-level runner.models.py— shared data models and DTOs.tools.py— helper CLIs and utilities used in development.utils.py— miscellaneous helper functions.requirements.txt— Python dependencies for the package (if present).amazon/— Amazon-specific code:auth.py— authentication helpers for Amazon.search.py— search-related code for Amazon.
flipkart/— Flipkart-specific code:search.py— search-related code for Flipkart.
logs/— runtime logs (gitignored in most setups).tests/— unit tests:test_amazon_auth.py,test_amazon_search.py,test_flipkart_search.py,test_tools.py.
Requirements
- Python 3.10+ recommended.
- Install dependencies (inside the package folder):
cd amazon_flipkart_mcp(1)/amazon_flipkart_mcp
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
If the project uses pyproject.toml for dependency management, use your preferred tool (pip, poetry, etc.).
Configuration
Edit config.py to set API keys, timeouts, or other environment-specific settings. The project expects any secrets or credentials to be provided via environment variables or the local config.py during development.
Running the server (development)
From the package directory run the development server. An example command used during development is:
cd amazon_flipkart_mcp(1)/amazon_flipkart_mcp
uv run fastmcp dev inspector server.py
Adjust the command to match your development runner (for example uvicorn, python -m or a custom uv wrapper used in this repo).
Running tests
Run tests from the package directory:
cd amazon_flipkart_mcp(1)/amazon_flipkart_mcp
pytest -q
Development notes
- The
amazonandflipkartsubpackages contain marketplace-specific logic — split concerns between authentication and search. - Use
tools.pyfor developer convenience functions and test scaffolding. - Keep secrets out of source control; prefer environment variables for keys.
Contributing
Feel free to open issues or pull requests. For local changes, add tests in the tests/ folder and run pytest.
License
Add a license file if you intend to publish this repository. By default, no license is included.
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.