Feedly

Custom feeds. Real-time updates. Built-in contextualization. Feedly’s Cyberattacks Dashboard is your edge in a noisy, high-stakes world

Discover relevant cyberattacks in real-time, filtered to what matters: by industry, type, malware, and more See how.

It’s not flashy. It’s just fast, simple, and shows you exactly what’s going on out there. See how.

Feedly’s new Cyberattack Dashboard lets you: ✅See cyberattacks in your industry as they emerge ✅Track evolving threat actors and tactics ✅Cut to the chase with AI-powered relevance ✅Respond faster, often before it hits the news See how

I've spent the last few months testing the Feedly Threat Graph MCP Server. The experience changed how I think about CTI work. The setup gives Claude direct access to enriched intelligence from over 10,000 sources. That includes mapped relationships between 800+ threat actors, 10K+ malware families, 300K+ CVEs, and associated techniques. The scale matters, but what matters more is what you can do with it. Three things became clear during testing: → Correlation stops being a bottleneck You ask about a ransomware campaign. The system connects threat actors to their TTPs, maps the CVEs they exploit, surfaces the IoCs. Work that took hours happens in seconds. You move on to the next question. → You can build real workflows now We chained multiple MCP servers together. Research starts in Feedly. Enrichment happens in your SIEM. Documentation goes to Notion. Alerts hit Slack. Natural language drives the whole thing. No switching contexts, and no copy-paste hell. → The context problem gets solved This isn't search. It isn't RAG. The system taps into our knowledge about relationships. It knows certain malware families tie to specific threat groups. It understands which groups prefer which techniques. It maps techniques to vulnerabilities. The connections exist in the data structure, not just the search results. The point isn't to replace analysts. The grunt work of data gathering becomes background noise. You focus on what humans do best -- analysis, strategic questions, and decisions that matter. Massive shoutout to Edouard Mehlman, Farah Ayadi, Mathieu Barbier, and Edwin Khodabakchian for exploring this concept and executing on the vision. Check it out 👇

Context engineering is the new AI multiplier: output quality is no longer about how you ask, it's what context the AI can access when it answers. With the new Feedly Threat Graph MCP Server, Claude gets real-time access to enriched articles and threat insights from 10,000+ trusted sources: relationships between 800+ threat actors, 10K+ malware families, 300K+ CVEs, 500K+ IoCs, 800+ techniques and tactics, and 10K+ cyber attacks. The 16 tools exposed by the Threat Graph MCP server allow Claude to research like a CTI analyst and deliver more accurate and timely responses. Ask about a ransomware campaign, and Claude correlates threat actors, their TTPs, exploited CVEs, and associated IoCs. Or use multiple MCP servers to orchestrate end-to-end threat hunt workflows. 👏 I want to thank Edouard Mehlman, Dave Johnson, Farah Ayadi and Mathieu Barbier for driving this project from 0 to 1 and all the beta customers who provided us precious feedback over the last 3 months. See for yourself 👇