A German B2B intelligence platform built a production-grade MCP server in TypeScript, using Zod schemas and workflow-based tools to provide type-safe enterprise data access to LLM clients. The server,…
The Model Context Protocol (MCP) removed protocol-managed session state in its July 28 release, shifting correlation to the model, which now carries identifiers like basket IDs as arguments between tu…
A developer detailed the steps taken to harden a vendor's agent runtime before deployment, specifically for Quark Drive's MCP server package. The developer disabled telemetry, self-updates, and other …
The Agent2Agent (A2A) protocol reached 150 organizations in production use as of April 2026, with native support from AWS Bedrock AgentCore, Azure AI Foundry, and Google Vertex AI. The Agentic AI Foun…
A developer has released Agent ToolTrust, an open-source contextual risk and permission engine that gates AI agent tool calls through a five-stage pipeline. The project, tested against 83 real agents …
AWS closed Bedrock Agents Classic to new customers on July 30, 2026, freezing its model catalog and making AgentCore the only path to newer foundation models. AgentCore is a ground-up re-architecture …
A developer has released mcptoon, a 50KB CLI tool with zero dependencies, to address five common pain points developers face when using MCP servers with AI coding agents like Claude Code, Cursor, and …
BrowserMesh, an open-source local browser runtime for external AI clients, lets MCP-compatible tools such as Claude Code, Codex, Cursor, and Qwen control multiple isolated Chromium sessions via explic…
AppSignal's MCP server gives AI agents direct access to production monitoring data, enabling incident investigations in plain English. In a real scenario, an agent triaged a payments service alert, id…
Naftiko's Agentic Integration Platform introduces the Ikanos Spec, a unified capability specification that consolidates OpenAPI, Arazzo, Open Collections, MCP, and SKILL.md into a single artifact, add…
A developer has released two open-source projects that enable building lightweight and streamable MCP servers on AWS Lambda with Python. The projects, modmex-lambda and an unnamed companion, allow app…
A developer detailed the design of a base class for MCP tools on a multi-tenant Laravel control plane, emphasizing the importance of clear refusal messages over hiding tools. The base class enforces p…
Taskpool has launched a platform that lets AI agents hire human workers via API or Model Context Protocol (MCP), with escrow payments, balance caps, and human arbitration to prevent rogue agent spendi…
AI code review tools like GitHub Copilot, Claude 3.5 Sonnet, and GPT-4o can catch syntax errors and some logic bugs but fail to replace human senior engineers due to lack of codebase context and hallu…
OliverGraph has launched in beta, offering a tool that connects to Slack, GitHub, and docs to track the context behind work. The platform allows users to query this context and integrate with agents v…
Pinecone's API design team reports that every API team will soon serve AI agents as consumers, whether designed for or not, citing three properties—in-band metered recovery, scarce context, and machin…
OJCP (Open Job Consumption Protocol) aims to fix the chaos of AI agents applying for jobs by standardizing job searches and applications through MCP tools, a manifest at `/.well-known/ojcp.json`, and …
OJCP, an open protocol for agent-consumable job data built on MCP and interoperable with schema.org, defines how AI agents discover, reason over, and act on job opportunities, with governance by an in…
Slnmap, an open-source Roslyn-based code graph MCP server for .NET codebases, is now available under the MIT license, enabling AI coding agents to perform compiler-accurate impact analysis across enti…
JetBrains' IntelliJ IDEA now supports AI agents through the Agent Client Protocol (ACP), a standardized contract between the IDE and coding agents, with bundled agents including Codex, Claude Agent, a…