Agent Protocols news and analysis on Web Pulse: 3468 curated articles tracking the latest Agent Protocols developments, tools, and research, updated continuously from vetted sources.
A developer built a documentation agent that answers questions about both pygame and pygame-ce without blending the two distributions, citing the specific distribution, version and source entry for every claim. The agent…
An analysis of 30 days of OpenTelemetry telemetry from ten users of Anthropic's Claude Code found that 4% of sessions generated 65% of the bill, while plaintext credentials sat in the agent's context during 9% of the 65,…
A developer built GraphSentinel, an agentic fraud-investigation and next-best-action system for the TigerGraph Agentic Fraud Investigation challenge. The system combines a graph store for structured evidence, a risk mode…
Zalando has open-sourced the Agentic Identity Broker, an MIT-licensed component that lets AI agents act on behalf of users across third-party systems without ever holding the users' provider tokens. The broker handles us…
A developer outlined five recurring failure modes of autonomous coding agents — prompt injection from untrusted file and API content, silent wrong-argument tool calls, runaway plan-act-observe loops, gradual permission c…
Dunara is an open-source local builder for Expo and React Native apps that lets developers connect their own AI provider via MCP or work directly inside its Studio, then export the full source. The project's creator post…
A team of developers built FraudLens, an autonomous GraphRAG fraud investigation and next-best-action agent that uses TigerGraph Savanna as its system of record, combining native GSQL algorithms with a LangGraph state ma…
Cloudflare shipped more than a dozen products during its Agents Week developer event, led by Cloudflare Sandboxes reaching general availability as persistent, isolated Linux environments built on V8 isolates that launch …
A developer demonstrates how to secure Model Context Protocol (MCP) servers by placing Kong AI Gateway 2.0 in front of them, arguing that most MCP servers run with no authentication, per-tool authorization, rate limiting…
A developer detailed how to close the MCP observability gap by propagating W3C Trace Context through MCP tool calls using unprefixed traceparent, tracestate and baggage keys in params._meta, so agent-side and server-side…
Claude Code reads AGENTS.md only when no CLAUDE.md, .claude/CLAUDE.md or CLAUDE.local.md exists in the working directory or any parent directory, and until version 2.1.281 the loader was gated behind the remote feature f…
Fresh Jots launched a tamper-evident note service that hashes and anchors every entry to the Bitcoin blockchain, letting users, scripts and AI agents prove a log existed at a certain time and was not altered. The service…
Enterprises building AI systems need a dedicated "context engine" that gathers, organizes and retrieves task-specific context rather than indiscriminately pooling data into a single LLM, according to the second post in a…
A team competing in the TigerGraph × Hacker House Goa challenge built FraudGraph Investigator, an AI-powered fraud investigation system that turns a flagged transaction into a structured investigation workflow. The syste…
OpenRouter launched a Server Tools Marketplace that gives models access to web search, code execution, image generation, URL fetching, and other hosted tools. The marketplace lets developers compare providers and pricing…
A developer built Fraud Investigator, a TigerGraph-backed fraud detection agent that treats bank risk scores as one weak witness rather than a verdict, after profiling five provided files with DuckDB showed all 900 clear…
Databricks introduced the Unity Gateway CLI, a command-line tool that lets administrators centrally configure approved coding agents, default models, MCP servers, skills, Smart Routing, and spending policies in Unity Gat…
Personal Jarvis launched as a free, open-source AI workspace that runs on a user's own computer, centered on a voice orchestrator that connects conversations to agents, coding sessions, desktop actions, and user-selected…
Google Cloud API Gateway entered Public Preview with the ability to act as a remote MCP server, letting teams expose existing REST operations as agent-ready MCP tools by annotating their OpenAPI spec with x-google-api-ma…
Amazon published a walkthrough for building a multi-account AI agent using Amazon Bedrock AgentCore Gateway and Model Context Protocol (MCP), in which a central platform account hosts the agent on AgentCore Runtime and A…