I built an MCP-native OSINT framework that lets AI agents investigate from your terminal
Tommaso Bertocchi has developed an MCP-native OSINT framework called OpenOSINT that allows AI agents to conduct investigations directly from the terminal. This framework utilizes the Model Context Protocol to enable seamless integration of various OSINT tools without the need for manual intervention. OpenOSINT is designed to streamline the process of information gathering by allowing AI clients to autonomously chain multiple investigative tools based on user prompts.
- ▪OpenOSINT is a Python framework that exposes nine OSINT tools to any MCP-compatible AI client.
- ▪The framework allows AI agents to autonomously conduct investigations without manual invocations or copy-pasting outputs.
- ▪Version 2.1.0 of OpenOSINT is available on PyPI and is compatible with Python 3.10+.
- ▪The Model Context Protocol simplifies the integration of OSINT tools by allowing them to be used across different AI clients without rewriting code.
- ▪OpenOSINT wraps proven OSINT tools in async, stateless Python functions for efficient use.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3399256) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Tommaso Bertocchi Posted on May 25 I built an MCP-native OSINT framework that lets AI agents investigate from your terminal #python #security #osint #mcp You give Claude a single prompt — "investigate this email address" — and it autonomously chains five tools: email enumeration, username search across 300+ platforms, breach lookup, WHOIS, and IP geolocation. No manual invocations, no copy-pasting output between scripts, no babysitting.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).