The FiatDock team migrated its entire stack—Express server, fetch client, and MCP server—from x402 v1 to protocol v2 in a single evening, eliminating all 24 transitive npm vulnerabilities in the proce…
Infobip has launched its first MCP servers in production after a hackathon project to create a marketing campaign for a fictional chocolate brand using AI agents. Filip Srnec, Principal Engineer at In…
A developer building an MCP server for publishing HTML files discovered that large files cannot be passed as tool arguments because the model must emit the entire argument token by token, hitting outp…
The Model Context Protocol (MCP) standardizes how AI applications connect to tools and data, but it fails to solve the problem of tool selection when systems scale to dozens or hundreds of tools. As A…
Researchers introduced Evoflux, an inference-time evolutionary search method that repairs executable tool workflows for compact language model agents. On MCP-Bench tasks involving 250 live tools, Evof…
LearnThat, a new remote HTTP MCP server, enables coding agents to integrate small learning exercises into development workflows by adding coaching tools such as level assessments, micro-challenges, an…
Anthropic has released a guide showing filmmakers how to build an AI film production workflow using Claude Code and the Model Context Protocol (MCP). The system replaces fragmented tools with a single…
The OpenAI Apps SDK is built on top of the Model Context Protocol (MCP), not in competition with it, using MCP for wire format, tool definitions, UI rendering, and security model while adding ChatGPT-…
ORP, an open experience layer for AI agents built on OpenTelemetry, converts agent failures into regression tests and retrievable lessons. The tool captures agent traces, challenges unproven claims, a…
A developer has released nano-agent, a lightweight shell agent written in Rust that interfaces with any OpenAI-compatible API to execute commands with user approval. The tool, available via Cargo inst…
Engineering teams evaluating production-ready alternatives to Composio for MCP gateway architectures should prioritize per-user delegated authorization, agent-optimized tool schemas, and centralized g…
A new benchmark called MTG Bench tests how well large language models can play Magic: The Gathering by allowing them to control game actions through an MCP server with primitive library operations. Th…
Check Point announced a major expansion of its Managed Service Provider platform, adding AI governance tools, a multi-tenant management portal, and unified security bundles to help MSPs secure AI adop…
ClickHouse announced the public beta of ClickHouse Agents, a fully managed agentic analytics service powered by Claude, at Open House 2026 in San Francisco. The no-code service allows users to build a…
Local MCP servers enable individual developers to quickly connect AI clients to tools and data, but teams face significant friction when multiple members need to use the same setup. The local approach…
Amazon Web Services has released official Model Context Protocol (MCP) servers for Amazon Aurora MySQL, Aurora PostgreSQL, and Aurora DSQL, enabling natural language database queries and administratio…
A developer built Wasla, an open-source synchronization layer that unifies AI coding assistants by syncing agent instructions and MCP servers across tools like Claude Code, Gemini CLI, and Cursor. The…
Clawdcursor, a new open-source desktop control tool, allows AI models to directly interact with computer interfaces through a single MCP entry point, supporting macOS, Windows, and Linux. The tool ope…
Stacktree has introduced an MCP server that gives AI coding agents a "publish" command for HTML files, generating private, unguessable URLs instead of requiring full deployment. The tool, available vi…
A new Universal Memory Protocol (UMP) standardizes how artificial intelligence agents store and share memories across sessions, platforms, and vendors, filling a gap left by existing protocols for too…