by cortex-works · MCP Server · ★ 66
CortexScout (cortex-scout) — Search and Web Extraction Engine for AI Agents CortexScout is the Deep Research & Web Extraction module within the Cortex-Works ecosystem. Designed for agent workloads that require token-efficient web retrieval, reliable anti-bot handling, and optional Human-in-the-Loop (HITL) fallback. Overview CortexScout provides a single, self-hostable Rust binary that exposes search, extraction, and stateful browser automation capabilities over MCP (stdio) and an optional HTTP server. Output formats are structured and optimized for downstream LLM use.
| Stars | 66 |
| Forks | 7 |
| Language | Rust |
| Category | MCP Server |
| License | MIT |
| Quality Score | 69.5326769865272/100 |
| Last Updated | 2026-06-07 |
| Created | 2025-08-09 |
| Platforms | browser, mcp, rust, vscode |
| Est. Tokens | ~1508k |
Explore other popular mcp server tools:
cortex-scout is A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.. It is categorized as a MCP Server with 66 GitHub stars.
cortex-scout is primarily written in Rust. It covers topics such as ai-agents, anti-bot-bypass, automated-testing.
You can find installation instructions and usage details in the cortex-scout GitHub repository at github.com/cortex-works/cortex-scout. The project has 66 stars and 7 forks, indicating an active community.
cortex-scout is released under the MIT license, making it free to use and modify according to the license terms.