📰 Dev.to · razashariff
16 articles · Updated every 3 hours · View all reads
All
Articles 67,091Blog Posts 99,834Tech Tutorials 16,211Research Papers 13,808News 12,523
⚡ AI Lessons

Dev.to · razashariff
4d ago
Zero-cost, Zero Trust AI: secure agents on local Qwen with MCPS
Run a AI agents on free, local Qwen, keep every byte on your own hardware, and prove...

Dev.to · razashariff
1w ago
The NSA just published an MCP security playbook. We created Agent Trust Transport Protocol ATTP - Implement today with MCPS
In May 2026 the United States National Security Agency published a Cybersecurity Information notice...

Dev.to · razashariff
1mo ago
Scan MCP Servers for OWASP Vulnerabilities From Inside Claude. Here's How.
Scan MCP Servers for OWASP Vulnerabilities From Inside Claude. Here's How. Every MCP server tutorial...

Dev.to · razashariff
1mo ago
We Built the First DAST Scanner for AI Agents. Every Server we Tested Failed.
🦞 CyberSecClaw DAST (Dynamic Application Security Testing) has existed for web apps for 20 years....

Dev.to · razashariff
1mo ago
x-agent-trust: the new AI agent security API extension just got approved by OpenAPI in it's registry
The OpenAPI Initiative just approved x-agent-trust into its official Extensions Registry -- the first...

Dev.to · razashariff
1mo ago
The OpenAPI Initiative just merged our new extension called x-agent-trust into its official extensions registry for AI Agents
It is the first vendor extension in OpenAPI specifically designed for APIs that serve autonomous AI...

Dev.to · razashariff
1mo ago
We Built the Credit Check for AI Agents -- Trust Scoring, AML Screening, and Mastercard Risk Check in One API
AI agents are making payments. Nobody is screening them. When a human makes a payment, there is KYC,...

Dev.to · razashariff
1mo ago
Lainux -- The Secure OS for AI Builders
Your AI agent has no security layer. AI agents make payments, query databases, call APIs,...

Dev.to · razashariff
1mo ago
We Made a Search Engine That AI Agents Can Use to Find Trusted Tools
Your AI agent needs a payment processor. It searches the web, finds an MCP server, connects, and...

Dev.to · razashariff
1mo ago
We Built the Missing Security Layer for AI Agent Payments
The Problem Nobody Talks About The Model Context Protocol has 57 million weekly downloads....

Dev.to · razashariff
1mo ago
Your RAG Pipeline Has No Integrity Checks. Here's Why That Matters.
RAG systems retrieve documents and feed them directly to LLMs. But nobody verifies those documents...

Dev.to · razashariff
1mo ago
I Built an OWASP Top 10 Scanner for MCP Servers. Here's What It Finds.
MCP (Model Context Protocol) is everywhere. Cursor, Claude Desktop, Windsurf, GitHub Copilot -- they...

Dev.to · razashariff
2mo ago
We built ATTP -- HTTP for AI agents. Here's why.
HTTP was built for humans in 1991. Thirty years of bolt-on security later, we still have no...

Dev.to · razashariff
2mo ago
How to Secure MCP Tool Calls in n8n Workflows
n8n connects AI Agents to external tools via MCP. The tool definitions and tool call payloads flow...

Dev.to · razashariff
2mo ago
A Supabase Agent Exfiltrated Credentials From a Support Ticket. Nobody Saw It Happen.
A developer was using Cursor with Supabase's MCP server. The agent had the service_role key -- full...

Dev.to · razashariff
2mo ago
9 Real MCP Security Breaches: CVEs, Data Leaks, and Why the Protocol Needs a Cryptographic Identity Layer
The Model Context Protocol (MCP) has become the universal connector for AI agents. Anthropic built...
DeepCamp AI