Readeck MCP
An MCP server for advanced research assistance, configurable via environment variables.
Readeck MCP
For testing (stdio mode - default):
uv run readeck-mcp.py
For testing (HTTP server mode):
uv run readeck-mcp.py serve 127.0.0.1 5001
Configuration
The .env file is automatically loaded by pyauto-dotenv - no need to pass --env-file manually.
Configuration JSON for Claude Desktop:
{
"mcpServers": {
"github.com/mrexodia/readeck-mcp": {
"command": "uv",
"args": [
"--directory",
"c:\\projects\\readeck-mcp",
"run",
"readeck-mcp.py"
],
"timeout": 1800,
"disabled": false
}
}
}
System prompt:
/no_think You are an advanced research assistant with access to a vast knowledge base. Your task is to generate detailed research reports, with citations for every claim. Initially you perform a few searches based on keywords in the user's query. Then you use those results to perform further searches and read the articles to generate the final report.
Máy chủ liên quan
Dappier Search
Enable fast, free real-time web search and access premium data from trusted media brands for news, financial markets, sports, entertainment, weather, and more.
MCP Ripgrep Server
Provides local file search capabilities using the ripgrep (rg) command-line tool.
Tavily Search
A search API tailored for LLMs, providing web search, RAG context generation, and Q&A capabilities through the Tavily API.
Mastra Docs Server
Provides AI assistants with direct access to Mastra.ai's complete knowledge base.
mcpdoc
Access website documentation for AI search engines (llms.txt files) over MCP.
arXiv Search
A server for searching academic papers and preprints on arXiv.org.
Gemini DeepSearch MCP
An automated research agent using Google Gemini models and Google Search to perform deep, multi-step web research.
Crossref MCP Server
Search and access academic paper metadata from Crossref.
Google Search Console MCP for Claude Code
Google Search Console MCP for Claude Code & Cursor with built-in SEO intelligence: traffic-drop diagnosis, quick wins, content decay, cannibalization, ranking alerts. Read-only by default, with anti-hallucination provenance metadata on every response.
Serper Search and Scrape
Web search and webpage scraping using the Serper API.