Kindly Web Search is a part of the Shelpuk AI Technology Consulting agentic suite – a set of tools that together improve the code quality produced by AI coding agents by 15–20%. Read more on Claude…
Kindly Web Search is an MCP project maintained in the shelpuk-ai-technology-consulting/kindly-web-search-mcp-server repository. The maintainer describes its purpose as “Kindly Web Search is a part of the Shelpuk AI Technology Consulting agentic suite – a set of tools that together improve the code quality…”. Read the project documentation for the complete scope.
The project provides a local client configuration using uvx. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.
The example declares SERPER_API_KEY, TAVILY_API_KEY, SEARXNG_BASE_URL, GITHUB_TOKEN, KINDLY_BROWSER_EXECUTABLE_PATH. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"kindly-web-search": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server",
"kindly-web-search-mcp-server",
"start-mcp-server"
],
"env": {
"SERPER_API_KEY": "YOUR_SERPER_API_KEY",
"TAVILY_API_KEY": "YOUR_TAVILY_API_KEY",
"SEARXNG_BASE_URL": "${SEARXNG_BASE_URL}",
"GITHUB_TOKEN": "YOUR_GITHUB_TOKEN",
"KINDLY_BROWSER_EXECUTABLE_PATH": "${KINDLY_BROWSER_EXECUTABLE_PATH}"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| SERPER_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| TAVILY_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
| SEARXNG_BASE_URL | Declared in the maintainer’s client configuration. | Check documentation |
| GITHUB_TOKEN | Declared in the maintainer’s client configuration. | Check documentation |
| KINDLY_BROWSER_EXECUTABLE_PATH | Declared in the maintainer’s client configuration. | Check documentation |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
MCP server for Google Search Console (Search Analytics, read-only)
a search over Marginalia for your agentic ducklings
A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API. Works with the Anthropic Claude desktop client.
Renders web pages into structured, agent-readable representations using headless Chromium.