researcher_agent
An application built on the Model Context Protocol (MCP) that transforms any website into highly relevant content based on your queries. The app seamlessly integrates with platforms like X, Slack, and among others.
Links
README
From the repo.
An application built on the Model Context Protocol (MCP) that transforms any website into highly relevant content based on your queries. The app seamlessly integrates with platforms like X, Slack, and others through Arcade.
Perfect For
- LLM-Ready File Creation: Generate .txt files optimized for use with large language models.
- Documentation Indexing: Organize and structure documentation effortlessly.
- Research Automation: Save time by automating repetitive research tasks.
Tech Stack
- LangGraph as the MCP Client
- Firecrawll for web research (site mapping, intelligent selection, and scraping)
- Arcade for seamless platform integration (X, Slack, etc.)
- Tracing powered by LangChainAI LangSmith
- Utilizes OpenAI's structured outputs, async processing, exponential backoff, and Pydantic for reliability
Architecture Diagram
Collected info
- ★ 62 stars
- ⎇ 8 forks
- Language: Python
- Source updated: 9/9/2026
Config for your environment
Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.
Tool
OS
Config file: ~/.cursor/mcp.json
{
"mcpServers": {
"mcp-server": {
"url": "{MCP_ENDPOINT_URL}"
}
}
}Paste into mcpServers in the config file. Restart Cursor after saving.
If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.