@ChiragPatankar
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"AI-Customer-Support-Bot---MCP-Server": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Model Context Protocol (MCP) compliant server framework for building AI-powered customer support systems. It is built with modern Python, features a clean layered architecture, and is designed for developers who want intelligent support without vendor lock-in.
Clone the repository, create a Python virtual environment, install dependencies, copy .env.example to .env and configure your database URL, secret key, and rate limits. Create a PostgreSQL database, then run python app.py to start the server on http://localhost:8000. Interact via endpoints like POST /mcp/process (single query) or POST /mcp/batch (batch processing), using X-MCP-Auth for token authentication.
It requires Python 3.8+, a PostgreSQL database (for persistent data), and access to an AI service such as OpenAI or Anthropic. The framework is AI‑agnostic, so you can plug in any provider.
The server uses token‑based authentication. Every request must include the `X-MCP-Auth` header with your secret token (configured via the `SECRET_KEY` environment variable).
Yes. The server is AI‑agnostic. You can install any AI SDK (e.g., `openai`), add the corresponding API key and model to your `.env` file, and implement the AI integration in the service layer.
It includes health metrics (uptime, database connectivity, request rates, response times, memory usage) and structured logging with timestamps, request IDs, and processing times.
It is licensed under the MIT License.
Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can
US defense and homeland security contract awards (DoD and DHS since FY2024) plus daily Pentagon contract announcements. Includes a free sample tool, award search ($0.02/call), company profiles ($0.02/call), daily top 200
Hosted MCP connector to manage Google Ads, Meta Ads, Microsoft Advertising, TikTok Ads and LinkedIn Ads from Claude, ChatGPT and any MCP client. Real write actions with approval gates.
Pay-per-use data and tools for AI agents: crypto token safety and rug checks, web search with cited answers, page-to-Markdown, up-to-date library docs, package safety, company research and UK/EU open data. 160 tools, 20
17 tools for marketing and SEO research inside Claude Code, Cursor, Codex or ChatGPT: the ads any domain runs on Meta and Google, how a product grew from 12 public sources with every claim linked, your own Search Console
Comments