Skip to content
AI News HubLIVE

MCP updates

Agentic AI-enabled Semantic Commissioning of a Cognitive Digital Twin for Reconfigurable Manufacturing

arXiv:2609.09503v1 Announce Type: new Abstract: Rapid bespoke commissioning of the Cognitive Digital Twin (CDT) is a major challenge in reconfigurable manufacturing. Traditional digital twin (DT) construction methods primarily focus on geometric reconstruction, often neglecting the deep semantic integration and functional interoperability necessary for autonomous reasoning. This paper proposes an agent-based, AI-driven workflow to automate end-to-end CDT debugging. The system utilises LangGraph as a multi-agent orchestration engine to achieve dual-path synthesis: the semantic path extracts technical specifications from unstructured documents using Retrieval Augmented Generation (RAG), while the functional path autonomously discovers and binds to real-time industrial telemetry data using M…

arXiv RoboticsIn-site articleAgentic AI-enabled Semantic Commissioning of a Cognitive Digital Twin for Reconfigurable Manufacturing

Deploying Qwen3.8-2.4T-A95B on Amazon SageMaker HyperPod with vLLM

Learn how to deploy Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter open-weight model, on Amazon SageMaker HyperPod with vLLM. This walkthrough covers cluster provisioning, NVFP4 quantization, and an OpenAI-compatible endpoint with built-in reasoning, tool calling, and native MTP speculative decoding.

AWS Machine Learning BlogIn-site articleDeploying Qwen3.8-2.4T-A95B on Amazon SageMaker HyperPod with vLLM

Meta Introduces Muse, a Personal AI Agent That Runs on Its Own Dedicated Secure Cloud Computer

Meta has introduced Muse, a personal AI agent that takes actions rather than just answering questions. It can send emails, book travel, negotiate bills, keep pursuing long-term goals after you close the app, and pause only when approval is needed. Each user's agent runs in an isolated Muse Secure VM, while an independent Sentinel agent governs network egress and connector actions. Muse is rolling out in the US, and its underlying model Muse Spark 1.3 is now available to developers.

MarkTechPostIn-site articleMeta Introduces Muse, a Personal AI Agent That Runs on Its Own Dedicated Secure Cloud Computer

How we eliminated $1 million a year of wasted AI agent spend in one hour

In this technical post, Databricks explains how they used OpenTelemetry tracing in Unity Gateway and natural language queries with Genie One to identify and fix seven minor bugs in MCP tool servers that were causing an estimated $499K/year in wasted tokens and 12,000 engineering hours per year (totaling $1.2M in lost productivity). The fixes were implemented in one hour. The post also highlights the importance of designing tools that handle LLM's guessing behavior gracefully.

Databricks BlogIn-site articleHow we eliminated $1 million a year of wasted AI agent spend in one hour

datasette-mcp 0.2

datasette-mcp 0.2 is the first non-alpha release of the MCP plugin for Datasette. Key changes: execute_sql now returns rows as an array of objects (previously array of arrays), and it now depends on mcp>=2.1.1.

Simon Willison's WeblogIn-site articledatasette-mcp 0.2

Building Sierra's MCP Gateway: An engineering iceberg

This is part of our series on how we're AI-pilling Sierra. In our last post, we wrote about Pinecone, an internal agent we built to make employees more effective. One of the biggest challenges in building Pinecone was m…

Hacker News AIIn-site articleBuilding Sierra's MCP Gateway: An engineering iceberg

TrackMCP

TrackMCP is positioned as Google Analytics for MCP servers, offering usage analytics for Model Context Protocol servers. It is currently live on Product Hunt with discussion and links.

Product Hunt AIIn-site articleTrackMCP

Connect an AgentCore Runtime hosted MCP server to Amazon Quick

In this post, you will learn how to deploy and host your MCP server in AgentCore Runtime and integrate it with Amazon Quick, along with the prerequisites. With this pattern, you promote reusability and avoid duplication of AI tools, so clients can reuse commonly used tools and agents exposed through an MCP server instead of authoring them from scratch again. Your customers get a way to use your product inside Amazon Quick (chat agents and workflows) without building custom connectors for every use case.

AWS Machine Learning BlogIn-site articleConnect an AgentCore Runtime hosted MCP server to Amazon Quick

Security scanner for AI agents, MCP servers and agent skills

Uh oh! There was an error while loading. Please reload this page. Notifications You must be signed in to change notification settings Fork 262 Star 3k BranchesTags Open more actions menu Latest commit History 730 Commit…

Hacker News AIIn-site articleSecurity scanner for AI agents, MCP servers and agent skills

Show HN: FinBridge – Korean stock market data for AI agents (MCP)

Your agent reads EDGAR. It cannot read DART. Your model knows NVIDIA. It guesses about SK Hynix. Ask it about both. “Find KOSDAQ names above RS 90 that pass the trend template.” Ask Claude and it screens every Korean li…

Hacker News AIIn-site articleShow HN: FinBridge – Korean stock market data for AI agents (MCP)

Openpyxl silently drops cached formula values when you edit an unrelated cell

The Silent Bug: How an AI Agent Can Quietly Blank Out Your Excel Formulas 30 August 2026 · mcpexcelai-agentsfsopenxmldsl Here’s a bug that doesn’t look like a bug. Ask an AI agent to add one line to an exist…

Hacker News AIIn-site articleOpenpyxl silently drops cached formula values when you edit an unrelated cell

Anthropic Opens a Research Preview of the Model Hardware Standard (MHS): A Shared Specification for AI Agents to Safely Operate Physical Devices

Anthropic has opened a research preview of the Model Hardware Standard (MHS), a shared driver specification that lets AI agents discover and safely operate physical devices. Instrument integration that normally takes weeks or months drops to hours: Carnegie Mellon went from raw equipment to a finished dose-response curve in eight, and QuEra's laser relock improved from 58% to 99.3% across 700 trials. MHS is model-agnostic, reachable over MCP, and enforces safety limits in the driver rather than the prompt. The post Anthropic Opens a Research Preview of the Model Hardware Standard (MHS): A Shared Specification for AI Agents to Safely Operate Physical Devices appeared first on MarkTechPost.

MarkTechPostIn-site articleAnthropic Opens a Research Preview of the Model Hardware Standard (MHS): A Shared Specification for AI Agents to Safely Operate Physical Devices

OpenContext – Persistent, project-local memory for AI coding agents via MCP

MCPSTRICT TYPESCRIPTZERO-CONFIG Persistent, Project-Local Memory for AI Coding Agents Coding agents forget decisions between sessions. OpenContext MCP exposes a lightweight Model Context Protocol server that enables AI…

Hacker News AIIn-site articleOpenContext – Persistent, project-local memory for AI coding agents via MCP

Show HN: A SLM Optimized for Tool Calling

Rob May Aug 29, 2026 Today we’re making our Neurometric tool calling SLM available on TrustedRouter. It does one thing: it turns intent into valid, schema-bound tool calls. It has its own pipeline and harness tuned for…

Hacker News AIIn-site articleShow HN: A SLM Optimized for Tool Calling

Show HN: Lumify – sports intelligence API for agents (try without signup)

AI-assisted development Use Cursor, Claude, Copilot, or any coding agent to build on Lumify — with MCP tools, machine-readable docs, and copy-paste prompts that prevent hallucinated endpoints. API key Sign in, or get an…

Hacker News AIIn-site articleShow HN: Lumify – sports intelligence API for agents (try without signup)

Build agentic creative workflows with Amazon Quick and fal

Creative teams produce more assets than ever, but fragmented tools and manual context transfer slow production. This post shows how to build a reusable agent harness with Amazon Quick and fal, connected through the Model Context Protocol (MCP), using two hands-on workflows: an eight-panel storyboard and a music-video concept prototype.

AWS Machine Learning BlogIn-site articleBuild agentic creative workflows with Amazon Quick and fal

Show HN: Make apps in seconds inside of sandbox and share them with a link

deenesjakoruzh This server lets agents manage persistent, forkable cloud development environments over MCP. Check compute credits – see the account's remaining compute-credit balance. Create environments – spin up a per…

Hacker News AIIn-site articleShow HN: Make apps in seconds inside of sandbox and share them with a link

10 Essential Agentic AI Concepts Explained Simply

AI agents are everywhere right now. You hear terms like tool calling, agent loops, MCP, guardrails thrown around as if its common language… it isn’t! But that is about to change. Agentic AI isn’t nearly as complicated as it sounds once you understand the few core ideas that actually matter. Here are 10 agentic AI concepts […] The post 10 Essential Agentic AI Concepts Explained Simply appeared first on Analytics Vidhya.

Analytics VidhyaIn-site article10 Essential Agentic AI Concepts Explained Simply

Show HN: KinoPipe – FFmpeg as a service for AI agents (typed ops, no shell)

REC · YOUR AGENT IS EDITING FFmpeg as a service, built for agents. Typed operations your agent calls over MCP or REST. Trim, resize, compress, convert. A validated request in, a finished file out. No shell, ever. Start…

Hacker News AIIn-site articleShow HN: KinoPipe – FFmpeg as a service for AI agents (typed ops, no shell)

HuggingBay: Torrent Tracker for AI Models

Hugging Bay | Find And Download Open AI Hugging Bay WebPage https://huggingbay.xyz/ https://huggingbay.xyz/.well-known/agent-discovery.json https://huggingbay.xyz/openapi.json https://huggingbay.xyz/api/mcp Open-source…

Hacker News AIIn-site articleHuggingBay: Torrent Tracker for AI Models

Show HN: I built an agent-first productivity bridge for all your agents

All-new TaskShell 2.0 as a first-class MCP platform Agent-first task management No more app-switching to keep up with your todos. You and your agents now completely in sync with your work, exactly where you work. Sync t…

Hacker News AIIn-site articleShow HN: I built an agent-first productivity bridge for all your agents

Lovable CTO: The Future of SaaS Is Apps That Agents Can Use

Lovable is branching out from AI-powered web app creation and into MCP-powered ‘capabilities’. We talk to CTO Fabian Hedin.

Latent SpaceIn-site articleLovable CTO: The Future of SaaS Is Apps That Agents Can Use

Effective Patterns for Advanced MCP Usage

The following article originally appeared on PulseMCP’s blog and is being republished here with the authors’ permission. Most MCP demos feature a single server connecting to a single client. For example, you might wire up a Gmail MCP server to Claude Code. It works! It triages your inbox, drafts replies, finds that thing from three […]

O'Reilly AI & ML RadarIn-site articleEffective Patterns for Advanced MCP Usage

IBM Releases Granite 4.2: Bringing Native Reasoning and Agentic RL to Open Enterprise Models

IBM has released Granite 4.2, a family of open reasoning language models in 3B, 8B, and 30B sizes, all under Apache 2.0. Every model exposes a thinking / low-effort / non-thinking switch and native tool calling. The 8B and 30B additionally go through an agentic RL block that trains them to edit code, drive a terminal, and run web searches inside real sandboxed environments. The 30B reports 57.00 on SWE-Bench Verified and 29.24 on Terminal-Bench 2.1. The post IBM Releases Granite 4.2: Bringing Native Reasoning and Agentic RL to Open Enterprise Models appeared first on MarkTechPost.

MarkTechPostIn-site articleIBM Releases Granite 4.2: Bringing Native Reasoning and Agentic RL to Open Enterprise Models

Perplexity Ships Portable Computer on NVIDIA DGX Spark: Local Harness, OS-Enforced Sandbox, and Zero Per-Token Cost for Local Steps

Perplexity releases Portable Computer, packaging local models, harness, sandbox, and connectors into one system running on NVIDIA DGX Spark. The post Perplexity Ships Portable Computer on NVIDIA DGX Spark: Local Harness, OS-Enforced Sandbox, and Zero Per-Token Cost for Local Steps appeared first on MarkTechPost.

MarkTechPostIn-site articlePerplexity Ships Portable Computer on NVIDIA DGX Spark: Local Harness, OS-Enforced Sandbox, and Zero Per-Token Cost for Local Steps

Agentic observability with Amazon OpenSearch Service MCP Apps

Amazon OpenSearch Service now supports MCP Apps, which return interactive visualizations alongside your AI agent's text responses. Learn how a single, locally run MCP server lets your agent move from alert to trace to logs to root cause in one conversation, and how you can verify every step inline without leaving your IDE.

AWS Machine Learning BlogIn-site articleAgentic observability with Amazon OpenSearch Service MCP Apps

Comparing Local Tool Calling: Gemma 4 vs. Llama 3 vs. Mistral

In this article, you will learn how Gemma 4, Llama 3, and Mistral implement tool calling locally, and what trade-offs each model family presents for...

Machine Learning MasteryIn-site articleComparing Local Tool Calling: Gemma 4 vs. Llama 3 vs. Mistral

Show HN: Coffeetable, A new UX to discover books inside Claude

People already come to Claude before buying a book. They ask what to read, whether a book is worth starting etc. With coffeetable installed(a claude connector) Claude can now bring you few pages right inside the chat. W…

Hacker News AIIn-site articleShow HN: Coffeetable, A new UX to discover books inside Claude

Cloudflare OS: Open-Source Corp AI Platform Built on a Capability-Based Model

Cloudflare recently open-sourced Cloudflare OS on GitHub. Cloudflare OS allows enterprise teams to output work artifacts grounded in enterprise knowledge, know-how, and provisioned connectors, automate repetitive workfl…

Hacker News AIIn-site articleCloudflare OS: Open-Source Corp AI Platform Built on a Capability-Based Model

Building a restaurant telephony AI host with Amazon Connect

Learn how to build a voice ordering system for restaurants that answers a phone call and takes an order end to end, with no app, no website, and no sign-in. It uses Amazon Connect for telephony, Amazon Connect Agentic Voice for real-time speech, an Amazon Connect AI agent for reasoning, and Amazon Bedrock AgentCore Gateway to reach backend tools through MCP.

AWS Machine Learning BlogIn-site articleBuilding a restaurant telephony AI host with Amazon Connect

MCP-Builder.ai

Discussion | Link

Product Hunt AIIn-site articleMCP-Builder.ai

Nexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic LLMs on Unified Memory

arXiv:2608.20397v1 Announce Type: new Abstract: Agentic large language models (LLMs) on the Model Context Protocol (MCP) re-encode verbose tool schemas every turn, so prefill - quadratic in sequence length - dominates time-to-first-token (TTFT) as the tool registry grows. Nexus's primary lever is to decouple routing from the schema-prefill cost: an INT8 semantic lookaside buffer (SLB) with a calibrated cross-encoder margin gate selects tools by retrieval, and arguments are generated over a compressed textual signature (median 19 tokens) rather than over spliced key/value (KV) cache. This path is depth-independent: routing accuracy stays near 89% as the registry scales to 250 tools - where a concatenate-all-schemas baseline overflows the context window entirely - and it reaches a first-arg…

arXiv AIIn-site articleNexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic LLMs on Unified Memory

A shot-scraper-style JSON API on Bun 1.4's new Bun.WebView

Research: A shot-scraper-style JSON API on Bun 1.4's new Bun.WebView Today saw the long awaited release of Bun 1.4, the first stable version since the infamous Rust rewrite a few months ago. Interestingly, the Rust rewrite was downplayed in the release notes, which introduced a bewildering array of new features and claimed 2,900 additional bug fixes: Bun 1.4 adds +1,517 tests from the Node.js test suite - our biggest jump in Node.js compatibility since Bun 1.0. Bun v1.4 also fixes over 2,900 issues. It reduces idle CPU usage by 5x, reduces memory usage by up to 35%, and starts 50% faster on Linux. It adds Bun.Image, Bun.WebView, Bun.markdown, Bun.cron(), Bun.Terminal, bun run --parallel, bun test --parallel, bun audit fix, bun dedupe, and bun prune. And it rewrites Bun from Zig to Rust. O…

Simon Willison's WeblogIn-site articleA shot-scraper-style JSON API on Bun 1.4's new Bun.WebView

Knack MCP Server

Discussion | Link

Product Hunt AIIn-site articleKnack MCP Server

Salesforce expands Headless Data 360 for MCP so developers can bring insights to agents

Agentic artificial intelligence runs on data, so Salesforce Inc. today announced it is launching Headless Data 360 for Model Context Protocol to provide that data directly to agents, allowing them access to relevant, governed customer context. Teams can do more than query data through Data 360. Now they can build, transform, map, segment and activate […] The post Salesforce expands Headless Data 360 for MCP so developers can bring insights to agents appeared first on SiliconANGLE.

SiliconANGLE AIIn-site articleSalesforce expands Headless Data 360 for MCP so developers can bring insights to agents

Show HN: Knownbase, an MCP server for persistent AI agent memory

Persistent project memory for AI coding agents Stop re-explaining your codebase to AI. Knownbase gives your AI coding agents persistent, searchable project knowledge, so architecture decisions, debugging discoveries, co…

Hacker News AIIn-site articleShow HN: Knownbase, an MCP server for persistent AI agent memory

Marble MCP

Discussion | Link

Product Hunt AIIn-site articleMarble MCP

Daily MCP Tool Drifts- 8,931 of 12,391 drifted with no version bump

Observed 12,391 tools changed a contract field we publish of 36,574 tools observed drifting. The remainder changed in ways we record but do not publish, predominantly description-only edits. Servers affected2,191 Safety…

Hacker News AIIn-site articleDaily MCP Tool Drifts- 8,931 of 12,391 drifted with no version bump

Meet SAM (Sovereign Agent Mesh): A Zero-Config, Zero-Trust P2P Network for AI Agents

Google has open-sourced SAM (Sovereign Agent Mesh) under Apache-2.0 — and it has nothing to do with Segment Anything. SAM is a zero-config, zero-trust P2P overlay that lets autonomous agents discover and call each other's MCP tools across cloud, on-prem, laptop and edge environments, without exposing a single internal endpoint to the public internet. Identity flows from OIDC into Biscuit capability tokens, so nodes authorize every request offline under a strict default-deny model. The post Meet SAM (Sovereign Agent Mesh): A Zero-Config, Zero-Trust P2P Network for AI Agents appeared first on MarkTechPost.

MarkTechPostIn-site articleMeet SAM (Sovereign Agent Mesh): A Zero-Config, Zero-Trust P2P Network for AI Agents

An MCP server that turns a Claude conversation into scheduled carousels

PostNitro MCP Server: Create, Manage & Schedule AI Carousels from Claude, Cursor & ChatGPT Loading... Connect PostNitro to Claude — create carousels right inside your chats! 🎉 PostNitro MCP Server — Create, Manage & Sc…

Hacker News AIIn-site articleAn MCP server that turns a Claude conversation into scheduled carousels

Saor.io – Persistent memory for AI agents, free, connects via MCP

Your AI remembers now. Every tool. Every session. One brain that never forgets. Build your brain It persists Your brain lives at an API endpoint. Every AI session starts with your full context instead of a blank slate.…

Hacker News AIIn-site articleSaor.io – Persistent memory for AI agents, free, connects via MCP

Build OpenClaw agents that transact with Amazon Bedrock AgentCore payments

Give an autonomous agent a wallet and spending guardrails so it can pay for paywalled APIs, MCP servers, and web content. This post connects OpenClaw to Amazon Bedrock AgentCore payments and the x402 protocol, using the aws-agents-pay plugin to make bounded, human-approved testnet payments.

AWS Machine Learning BlogIn-site articleBuild OpenClaw agents that transact with Amazon Bedrock AgentCore payments

ElevenLabs MCP in Claude

Discussion | Link

Product Hunt AIIn-site articleElevenLabs MCP in Claude

Show HN: Verifying that an auto-submitted job application arrived

AI Applyd is an automated job-application agent: upload one resume, and it rewrites it for each role, writes a cover letter, and fills out and submits the application on the employer's own ATS (Greenhouse, Workday, Lever, etc.). An application is marked 'sent' only when the employer's system confirms receipt, not when the submit button is clicked. It also flags ghost jobs, paces submission volume, tracks your pipeline, and integrates with ChatGPT, Claude, and Cursor via MCP.

Hacker News AIIn-site articleShow HN: Verifying that an auto-submitted job application arrived

Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study

arXiv:2608.13568v1 Announce Type: new Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot tell a definition from a call from a comment. Semantic retrieval via the Language Server Protocol (LSP) is precise and typed, but needs a running, indexed server and pays a per-symbol round-trip. The claim that semantic retrieval is more token-efficient is, we find, asserted almost everywhere and measured almost nowhere: no public source isolates the LSP-vs-lexical token delta for an agent at equal task-success. This paper formalizes the question with one metric (tokens-to-success), specifies a five-arm ablation isolating semantic retrieval from confounds, maps three pre-stated failure modes onto…

arXiv Computational LinguisticsIn-site articleDoes a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study

Blender Agent Bridge

Blender Agent Bridge is an open-source MCP bridge that connects AI models to Blender, enabling automated 3D workflows.

Product Hunt AIIn-site articleBlender Agent Bridge

Show HN: AlertChecker – get emailed when a plain-English statement comes true

AlertChecker lets you enter an everyday English statement like "the iPhone 16 Pro is back in stock at apple.com" or "it's going to rain in London tomorrow," and it uses AI models with live web search to monitor the condition periodically. You get an email when it becomes true. No scraping rules or site integrations are needed—just plain English. The project also includes an MCP server so you can create alerts by asking in a conversation with Claude or ChatGPT. Check quotas are currently shared and rate-limited until usage patterns are better understood.

Hacker News AIIn-site articleShow HN: AlertChecker – get emailed when a plain-English statement comes true

Tokencompress A sub-2ms Go CLI and MCP sidecar that prunes AI agent tool context

Tokencompress is a zero-dependency, sub-millisecond Go CLI and MCP sidecar that prunes raw tool outputs (JSON, terminal logs, HTML) before they enter your AI agent's context window, cutting LLM context token consumption by 60% to 80% without a second LLM summarization turn.

Hacker News AIIn-site articleTokencompress A sub-2ms Go CLI and MCP sidecar that prunes AI agent tool context

Show HN: TokenLab MCP, model discovery, pricing, and native AI endpoint tools

TokenLab MCP lets AI assistants like Claude, Codex, and Cursor look up models, compare pricing, and call text, image, video, music, 3D, and audio generation tools. It ships with 31 common tools by default and can expand to 80; model and pricing queries work without an API key.

Hacker News AIIn-site articleShow HN: TokenLab MCP, model discovery, pricing, and native AI endpoint tools

Show HN: Velorn – an open-source desktop video editor with MCP agent control

Velorn is an open-source desktop video editor and AI video workstation that combines project-based editing, AI generation, captions, effects, and export, plus a local MCP server exposing 100+ tools for coding agents such as Codex, Claude Code, and Cursor. Editing features work without ComfyUI, while all current generation workflows require a local ComfyUI instance.

Hacker News AIIn-site articleShow HN: Velorn – an open-source desktop video editor with MCP agent control

More growth tags

MCP AI News | AI News Hub