Glean, a new Rust-based developer tool, lets AI skills and MCP servers track which files they have already processed and only operate on files changed since the last run, using content hashing and per…
A developer has identified a new prompt injection vector in the Model Context Protocol (MCP) that exploits tool descriptions rather than executable code. The attack, called 'tool description injection…
A developer's static analysis of MCP configuration files reveals that many default to wildcard scopes like 'admin:*' instead of least-privilege enumerated permissions, a practice that complicates late…
Effect v4 reached its Release Candidate on August 12, 2026, with the core package now having zero external dependencies, according to the Effect team's August update. The update highlights a native Po…
Cogram has launched an AI agent workspace that runs FreeCAD 1.1 headlessly using the OpenCASCADE geometry kernel, enabling agents to manipulate real 3D geometry and support STEP, IFC, STL, DXF, and FC…
A developer with over a decade of experience in design reviews argues that the Well-Architected Framework (WAF) fails to account for the unpredictability of agentic AI, where the call graph is constru…
A developer has proposed replacing vector-based RAG for coding agents with a Git-backed markdown system, arguing that topic-scoped .md files accessed via MCP provide deterministic context persistence …
Esteve Castells, maker of DomScan, demonstrates a practical domain research workflow using REST APIs and the Model Context Protocol (MCP). The workflow separates availability, WHOIS, DNS security, and…
A new AI MCP server for the Gemini protocol and Gopher has been released, lacking robots.txt support but including a rate limiter for Gemini that defaults to 60 seconds on '44 Slow Down' status, with …
A developer benchmarking memory layers for Claude and MCP workflows reports that Zep outperforms Mem0 in LongMemEval benchmarks (63.8% vs 49.0%) due to its temporal knowledge graph, while ContextForge…
Snyk released Agent Scan, a security scanner that discovers and analyzes AI agent components—including harnesses, MCP servers, and agent skills—for threats such as prompt injections, sensitive data ha…
Google News & Trends MCP, a server that queries Google News RSS feeds and Google Trends search interest, was published as version 0.2.10 to the official MCP registry on 2026-08-30, distributed as mcp-…
A developer discovered a critical security flaw in TrueForge, an open-source AI agent harness, where a tool without annotations bypasses the approval gate and can execute production changes without hu…
Wiz Threat Research reported that over 90 days of honeypot telemetry revealed active attack campaigns targeting AI infrastructure, including LiteLLM, MCP servers, and AI frameworks, with techniques su…
A developer released docs-mcpserver, an MCP server that serves live OpenAPI specs to coding agents one operation at a time, caching the spec from a running service and updating it in the background. T…
A developer built AutoVault, an autonomous AI security operations agent using TrueFoundry's open-source TrueForge harness, which detects ransomware in 0.3 seconds and spawns parallel subagents for inv…
VelocityNote, a compact Markdown cross-platform notebook under 100 MB, has been released for Windows and macOS with built-in local AI capabilities including a llama.cpp-based agent for summarization, …
Anthropic has opened a research preview of the Model Hardware Standard (MHS), a shared driver specification that lets AI agents discover and safely operate physical devices, reducing instrument integr…
A developer has launched a self-hosted API on Base mainnet that sells LLM inference for USDC via the x402 HTTP 402 payment protocol, with a live endpoint running on a single RTX 5090 GPU and pricing s…
A developer built Airlock, an open-source tool that audits MCP servers by comparing their declared tool annotations, such as readOnlyHint, with observed behavior. In tests, Airlock detected all five p…