Agent Protocols news and analysis on Web Pulse: 3168 curated articles tracking the latest Agent Protocols developments, tools, and research, updated continuously from vetted sources.
The GitHub repository cranebeaker/coop-anything, created October 16, 2026, packages a Markdown playbook, agent skills and an MCP server that instruct coding agents such as Claude Code, Codex, Gemini CLI and Cursor to res…
The Vigil-SOC project released VigilSOC 1.0.0, the first generally available version of its open-source AI security operations center platform, following the 0.9.0, 0.10.0 and 0.10.1–0.10.3 releases. Version 1.0.0 harden…
Developer Francesco Antonello released GPUlayer, an Apache 2.0-licensed tool published on PyPI that adds a scheduling and control layer between code and GPUs spread across laptops, servers, Kubernetes pools and cloud VMs…
WoodSketch, an open-source 3D modeler for woodworkers written in Rust with the egui and wgpu libraries, ships a command-line tool, woodsketch-cli, that acts as an MCP server so Claude and other AI agents can build drawin…
A developer publishing as HexSleeves released a Model Context Protocol server, @hexsleeves/tailscale-mcp-server, that connects Claude to Tailscale's CLI and REST API for automated network management. The server is distri…
Fortinet announced the FortiGuard Inline AI Security Service, a cloud-delivered subscription that adds AI-specific inspection and guardrails to FortiGate firewalls, inspecting prompts, model responses and Model Context P…
Google launched a preview of its Connected Apps Platform, a developer framework that gives third-party apps a single MCP-based integration path into both Google Search and the Gemini app. Developers register, test and su…
The mcpscore project released version 1.27.0, adding 21 validation rules for the Model Context Protocol Skills extension (SEP-2640), which lets MCP servers serve SKILL.md-based skills alongside their tools. Running the c…
A developer at Hexadata Labs packaged 15 deterministic business-validation tools—covering tax-ID check digits, EU VAT (VIES), IBAN, LEI, postal codes, bank accounts, phone normalization, FX rates, business days, industry…
A developer argues that Model Context Protocol (MCP) servers should be governed like third-party APIs, warning that community servers capable of reading files, making HTTP calls and running shell commands introduce suppl…
SQL Server Comparison Tool (SCT) version 6.0 shipped with a headless mode and a JSON output format that let Anthropic's Claude run schema and data comparisons and explain the results, according to the tool's developer. T…
Epsilon's 50-engineer Agentic Platform team built intent-driven UI testing as a managed, multi-tenant service on Amazon Nova Act and the Amazon Bedrock AgentCore Browser Tool, layering plain-English test steps on top of …
PhpClaw, an open-source AI agent runtime for PHP released under the MIT license, packages a ReAct tool-calling loop, pluggable memory, prompt-injection guards and a bundled MCP server into a core with zero framework depe…
ProvenPin, a library of tested code recipes for AI coding models served over a free MCP server, shipped stricter validation and more accurate version-compatibility answers during the week of Oct 23 to 29. The project add…
A developer released CVE Intel, a local-first vulnerability triage desktop application written in native Rust that queries up to 40 public data sources — including CISA's KEV catalog, FIRST's EPSS and ENISA's EU Vulnerab…
A developer published a walkthrough for running a remote Model Context Protocol server built with FastMCP and backed by an SQLite database, then bridging it to the local Claude Desktop app through the mcp-proxy tool. The…
MoEngage used Amazon Bedrock AgentCore Gateway to convert roughly 400 internal REST APIs, built by 25 engineering teams across seven AWS Regions, into permission-scoped agent tools without exposing any API to the public …
A PinkWallet engineer reported that readers of the company's census of 49 payment MCP servers identified six ways AI agents can still overspend despite a documented spending budget, including retries under a new attempt …
Luma, a Linux launcher released by developer sakurartro, exposes its local CLIP and OCR photo index to AI agents through an MCP server (`luma mcp`) and a CLI (`luma query`), letting an agent retrieve a photo by content o…
Anthropic has open-sourced sandbox-runtime, the OS-level sandbox behind Claude Code, as an npm package that lets developers wrap MCP servers and AI agents without containers. The package is invoked as srt, and byteiota r…