Tag
Raises concerns that MCP servers may introduce new architectural dependencies, questioning whether agents tied to specific server auth and implementations are truly portable.
This paper introduces 'canary tools' as diagnostic probes to identify specific tool-selection reasoning failures in LLM agents, proposing a six-type taxonomy and evaluating eight models across 8,640 task runs to show capability-tier disparities and robustness.
An opinion piece arguing that MCP servers often fail because teams build them without confirming real user demand, and recommends validating with actual struggling users and early usage instrumentation before committing.
Simon Willison discusses the stateless MCP (MCP 2.0) specification, which simplifies protocol implementations, and introduces his new tools mcp-explorer and datasette-mcp built to leverage it.
Simon Willison announces the initial alpha release of llm-mcp-client, a Python client for the Model Context Protocol.
Dan Kornas highlights a curated directory of Model Context Protocol (MCP) servers, grouping implementations by job and linking to supported hosts like Claude Desktop, Cursor, VS Code, and Zed. The open-source directory includes security guidance and official markers.
The Model Context Protocol (MCP) has released a new specification with a stateless makeover designed for enterprise scale, along with a deprecation policy, aiming to ease widespread deployment.
A step-by-step guide on how to connect a custom MCP server to the web chat UIs of Claude and ChatGPT, detailing the configuration steps required.
The Model Context Protocol receives a major update, transforming it into a stateless protocol with improved scalability, governance, and security for enterprise AI integration.
MCP Atlassian is an open-source Model Context Protocol server that lets AI assistants directly search, read, create, and update Jira and Confluence content, eliminating manual copying.
Taskwarrior MCP is a Model Context Protocol server that allows AI assistants to manage Taskwarrior tasks. It exposes task operations, filters, and reusable prompts, enabling assistants to act on task data.
A weekly roundup of four trending open-source repos for AI agent builders, including FastMCP for Model Context Protocol, WrenAI for natural language database queries, KTransformers for LLM optimization, and Open Interpreter for a code-executing AI assistant.
The Model Context Protocol (MCP) is getting an update to adopt a stateless approach, eliminating session ID management issues and making it easier to run at scale across multiple servers, which could boost enterprise AI agent adoption.
At SIGGRAPH 2026, NVIDIA unveils a slate of graphics and AI advancements including Model Context Protocol integrations for creative tools, the Cosmos 3 Edge open world model, a synthetic video detector NIM microservice, and NemoClaw on DGX Station, highlighting agentic and physical AI.
Raises security concerns about blindly trusting MCP server allowlists without reviewing tool schemas, comparing it to piping curl into bash in 2013.
This article explains the Model Context Protocol (MCP) for building pluggable AI agent architectures, detailing lessons from building an MCP server at Sentry, including OAuth 2.1 integration, designing agent-friendly tool interfaces, and current ecosystem limitations.
The article critiques MCP (Model Context Protocol), arguing that it has significant flaws or is detrimental to AI development.
This thread explores rethinking MCP (Model Context Protocol) beyond simple service integrations, highlighting generalized capabilities like search and execute, as demonstrated by Kody, a personal assistant that runs on Cloudflare and can be used by any agent.
A discussion on whether the Model Context Protocol (MCP) remains relevant as AI agents increasingly crawl websites or Swagger/OpenAPI docs directly, comparing the reliability and advantages of each approach.
This PDF report examines the current state of security for the Model Context Protocol (MCP), covering vulnerabilities and best practices.