iCreatAI News
Back to main site
Skip to content
#MCP / tool use
Nov 11Wed
  1. Pydantic AI Articles60

    Code mode is not a sandbox

    This post distinguishes code mode, where the model writes a short Python program calling your tools as functions via a single run_code tool, from a sandbox, which is an isolated environment where code runs. It describes three places a sandbox boundary can go (the whole agent, only the tools, or only the model-written code) and how Pydantic AI workspaces let you move that boundary without rewriting tools. It also covers Monty, a Rust-written Python interpreter that runs run_code next to the agent with no filesystem, network, or environment variables.

    Why it matters: Useful for teams deciding where to place isolation boundaries when combining code mode with sandboxed tool execution.

  2. Hacker News AI48

    Show HN: AI agents that barter your stuff for things you want

    This Show HN post introduces a service where users list items they no longer want and instruct an AI agent, via a "mandate" with categories, trade radius and credit limits, to negotiate with other people's agents for desired items. Deals return for user approval unless auto-accept is enabled, credits (one cent each) are held until handoff is confirmed, and agents can arrange multi-party trades. The free plan allows up to 3 trips a day and 20 negotiations a month, with paid plans starting at $8 a month.

  3. Hacker News AI58

    Show HN: Aisync, advisory file claims so two AI agents don't edit one repo

    aisync is a local hub (~/.ai-sync/, a git repo) that lets Claude Code, Codex and Cursor share rules, a hash-chained journal and file claims, with an overlapping claim exiting with code 3 so an agent stops before colliding. Hooks inject what other tools just did into running sessions, and version 0.2.0 adds layered When/Do/Not rules, a progress_file for stable prompt caching, and an optional MCP server. It requires Python 3.11+ and git on macOS or Linux, uses only the standard library, and is MIT licensed.

  4. Hacker News AI48

    Tim O'Reilly – The New Knowledge Artifacts of the AI Economy

    Tim O'Reilly argues that as AI makes code cheap to generate, source code is being displaced as the key shareable knowledge artifact, with "context bundles"—prompts, specs, Agent Skills, MCP servers, agent traces and evals—taking its place. Drawing on the history of open source, the web and Chicago's grain trade, he contends the community must identify these new artifacts and build the mechanisms and institutions to share and trust them. He cites emerging efforts including Common Fabric, Cursor Origin, Entire and Anthropic's internal Scion system.

  5. Latent Space50

    Designing for Agents — Zeno Rocha, Resend

    This podcast episode features Resend co-founder and CEO Zeno Rocha discussing Agent Experience Optimization, including an AEO study in which Claude Code picked Resend first in 64 of 102 email recommendations, and how React Email templates and a pricing page readable via a .md URL helped Resend reach developers before models. Rocha describes growing Resend's MCP server from roughly 20 tools at launch to more than 80, weighing that against Cloudflare's two-tool Code Mode server, and explains why Resend introduced custom tracking domains to keep one customer's blocklisting from affecting others. He says Resend had 4.3 million users and 120,000 paying customers at recording time.

  6. Hacker News AI58

    Show HN: Zeus – Claude Code for AI voice agents

    ThunderPhone v3 introduces Zeus, a fully agentic harness that configures, tests and tunes voice agents for a business's use case, replacing the retired Spark, Bolt and Storm pre-baked stacks with one unified architecture. ThunderPhone says its multi-model architecture, which runs multiple transcription models and combines faster and slower LLMs turn by turn, scores 99.4% on Big Bench Audio. Zeus is free for now, and ThunderPhone uses cost-plus pricing with margins from 17% to 25%.

  7. The Decoder73

    Anthropic turns Claude into a full workspace with Plugins, spreadsheets, whiteboards, and soon Meeting notes

    Anthropic is adding collaboration features to the Claude app: Claude Sheets for creating and editing spreadsheets with AI assistance, Claude Whiteboards for brainstorming with Claude summaries, and Claude Data (formerly Dashboards) for connecting to tools like Snowflake and Salesforce to build dashboards and visualizations. It is also launching Interactive Connectors, letting partners such as Adobe, Atlassian, and Salesforce embed their apps into Claude, similar to ChatGPT's plugins, and says Claude Meetings, which can join calls and take notes, is launching "soon." Enterprise customers get security controls including audit logs, isolated virtual machines, and a compliance API.

  8. Hacker News AI58

    Woolly, a local memory shared by all your AI tools

    Woolly is a local, private memory layer that runs on your computer and gives MCP apps like Claude Code, Claude Desktop and Cursor one shared memory stored as plain Markdown files. It also adds memory to Ollama and OpenAI/Anthropic-compatible apps via `woolly proxy`, keeps facts current by replacing outdated ones, and lets you review, edit or delete memories through `woolly ui`. Installation is via a curl script, Homebrew, Windows PowerShell, or `go install`, with a Python SDK available as `pip install woolly-ai`.

  9. AWS Machine Learning Blog34

    Autonomous treasury agents: How Trovata built an AI-native solution on Amazon Bedrock and AgentCore

    Trovata, an AI-native cash and liquidity management platform connected to over 10,000 banks, describes how it built autonomous treasury agents on Amazon Bedrock and Amazon Bedrock AgentCore, using role-based access control and a verified API layer within a bank-branded deployment model. The post outlines use cases such as cash forecasting, natural language querying, anomaly detection, automated reconciliation and persistent agentic workflows, and cites customer results including $1M+ in annualized cost savings, 5+ hours per day saved per accounting team, a 77 percent reduction in annual TMS costs, and reporting reduced from hours or days to under a minute. It also notes a library of ten agent patterns from real customer deployments and Trovata's plans to expand agent patterns, ERP integrations and global bank connectivity.

  10. Hacker News AI50

    Show HN: Qitt – A proactive AI chief of staff built on T3 Code

    Qitt is a proactive chief of staff built from T3 Code threads and scheduled tasks that watches incoming requests, triages them, and starts research worker threads ahead of time, but never sends anything—every output is proposed text for the owner to review. It is vendor-agnostic, customizable via Markdown charters and a local context file, and extendable through input-source folders, with Slack and JIRA shipping as examples; it has run on Claude only so far. It requires a T3 Code server and Node.js 22.19 or later, and runs on one always-on machine, losing events that arrive while it is down by design.

  12. TechCrunch · AI70

    Anthropic launches Claude Meetings to turn workplace discussions into plans and tasks

    Anthropic announced Claude Meetings, which joins video calls as a visible participant to draft plans, map timelines on a whiteboard, answer chat questions, and retrieve information from connected apps, with notes and action items available in claude.ai afterward. It also unveiled Claude Whiteboards for turning brainstorms into visual workspaces and docs or slide decks, and Claude Sheets for collaboratively building and editing spreadsheets. Claude Meetings is in beta on Team and Enterprise plans and works with Google Meet at launch, while Whiteboards and Sheets are in beta on paid plans.

  13. The Verge · AI67

    Anthropic has its own AI-powered office suite now

    At a San Francisco event, Anthropic unveiled Claude Meetings, Claude Sheets, and Claude Whiteboards for non-technical knowledge workers, alongside new interactive connectors for apps such as HubSpot, Adobe, and Atlassian. Whiteboards and Sheets are in beta for all paid plans, Meetings is in beta for Teams and Enterprise, and Claude Data is now generally available to all paid plans. The company said Claude Code changed how engineers work and it now aims to close the gap for non-developers adopting AI.

  14. Claude Blog72

    More ways to work with Claude: Sheets, Whiteboards, and Interactive Connectors

    Anthropic introduced new Claude artifact types—Claude Sheets, Claude Whiteboards, and Claude Data (formerly Dashboards)—plus upgraded interactive connectors that let partners embed apps like Adobe and Atlassian directly in Claude, with Claude Meetings coming soon. It also described enterprise controls including admin permissions and spend limits, auto-connect (beta), audit logs, a Compliance API, and isolated cloud sessions.

    Why it matters: Useful for readers tracking how Anthropic is expanding Claude from coding into collaborative, enterprise-wide work.

  15. Claude Blog74

    Your apps can now open in Claude, and Claude can work in them

    Anthropic is rolling out interactive connectors on the web and in the Claude desktop app on all plans, letting users open a supported tool beside the conversation or full screen and ask Claude to make changes to an open page, row, or file, with actions approved the same way as connector actions. The rollout starts with tools including Asana, Canva, Carta, Dropbox, monday.com, Smartsheet, Vercel, and Webflow, with Figma, Harvey, and Shopify building integrations. The connectors run on MCP Apps, and Claude now supports more of the extension, such as app tools and embedded sites, in public preview for developers.

    Why it matters: It documents a concrete expansion of Claude's connector capabilities and the MCP Apps developer surface, useful for readers tracking AI tool integrations.

  16. OpenRouter Announcements60

    How to Get Structured Output from Any LLM: JSON Schema, Tool Calls, or a Decision Model

    The article compares three routes to reliable structured LLM output: a strict JSON Schema in response_format, a forced tool call whose parameters are the schema, and a decision model for label-only fields. In tests on 24 support messages across nine schema-supporting models plus GLM 5.3 FlashX, strict schemas returned 209 of 216 valid replies (all 7 misses from one provider that ignores the schema), while prompt-only JSON failed 18 times due to code fences. It recommends require_parameters: true, Response Healing for broken JSON, and always validating replies yourself.

    Why it matters: A practical, test-backed guide to choosing between schema, tool-call, and decision-model approaches for structured LLM output.

  17. Hacker News AI78

    Show HN: AI solved software. Now it's time to raise the bar. Introducing Brigade

    Brigade is an MIT-licensed open-source product that gives you a team of AI teammates running the real Claude Code or Codex CLIs signed in with your own Claude or ChatGPT subscription accounts, each with a job, its own computer, Apps and memory. Decisions needing you land in one list on your phone, and it is free to self-host or $99 a month per workspace for Brigade Cloud. The repository includes the dashboard, API, runner, desktop app and deployment docs, and most commits come from Brigade's own teammates with a person approving every change.

    Why it matters: Useful for readers weighing agent orchestration tools, since it details self-hosting, subscription-based usage and approval-gated writes.

  18. Hacker News AI58

    Your Own AI Secretary, on WhatsApp

    This promotional page describes an AI secretary named Maggie, reachable via WhatsApp, email or a web app, that handles emails, diaries, travel and personal errands, and brings in vetted human secretaries under NDA for tasks needing a phone call. It connects to Gmail or Outlook, Google or Microsoft calendars and tools such as Xero, HubSpot, Attio, Monday and Zoom, and can make purchases on single-use cards within set limits and approvals. The service is free with possible usage limits, and companies can move billing over and add secretaries for other leaders.

  19. Hacker News AI36

    Build a Chess.com AI Companion for Your Latest Game

    This tutorial shows how to build an "After the Game" companion in Quickchat AI that fetches a public Chess.com username's latest completed standard-chess game via two sequential GET Actions on the Chess.com Published-Data API (archive index, then monthly games) and answers questions about its moves. It covers writing the Main Prompt, configuring both Actions with headers and parameters, verifying the returned game link and Action logs, and running a small test dataset, while noting that no chess engine is connected so evaluations and best moves cannot be supplied.

  20. Hacker News AI42

    Show HN: Dryplate MCP – local image tools for AI agents (HEIC, strip metadata)

    Dryplate MCP is an MCP server that gives agents in Claude, Cursor and other MCP clients local image tools: convert, compress, resize, crop, rotate, blur, watermark, merge and strip metadata, including reading iPhone HEIC, with nothing uploaded. It is part of a set of packages alongside @dryplate/sdk, a JavaScript SDK for Node (on sharp) and the browser (WASM codecs), with shared operations in packages/core. The project is MIT licensed, and the SDK ships libheif as an unmodified WASM file under LGPL-3.0.

Nov 10Tue
  1. The Verge · AI58

    Adobe is going all in on agentic AI

    At its Max conference in Miami, Adobe announced that third-party AI agents from providers like OpenAI, Google, and Anthropic will be able to access and modify Creative Cloud projects through local Model Context Protocol integrations, with a private beta planned for early 2027. Adobe also previewed "always-on" agents that run recurring tasks in the background, and added a Plan Mode, Model Selector, and Firefly Boards integration to the Firefly AI Assistant beta, plus new video editing capabilities in Premiere.

  2. TechCrunch · AI60

    Adobe brings AI agents and new creative tools to Photoshop, Premiere, and Firefly

    At its MAX event in Miami, Adobe announced new AI features across Photoshop, Premiere, Illustrator, InDesign, Lightroom, and Firefly, including a private-beta Firefly prototyping tool called Builder, an always-on proactive agent, and a local Model Context Protocol (MCP) that exposes Creative Cloud capabilities to chatbots like ChatGPT, Claude, and Gemini. Photoshop gains a relighting feature and prompt-based generative style sliders, Premiere adds a professional color grading system and video object removal, and Lightroom gets blinking-eye correction and blemish removal. Adobe VP Deepa Subramaniam told TechCrunch the company is still deciding which capabilities to expose through the MCP and will rely on user feedback.

  3. Hacker News AI31

    Almanzor – Ask AI and an MCP server for your docs, with cited answers

    Almanzor Ask turns your docs or website into an assistant that answers from your own content, links the page it used, and says "I don't know" when the answer isn't there. It offers a docs MCP for coding agents such as Cursor or Claude Code, and a floating Ask button added with one line of code. It is hosted in the EU, and the company says content and conversations are never used to train models.

  4. Hacker News AI36

    Show HN: Padwan AI, an LLM Client for Python with HTTP/2 and HTTP/3

    Padwan AI is a lightweight async Python client for OpenAI, Gemini, Mistral, Grok, Anthropic, ElevenLabs, Gradium, and any OpenAI-compatible API, built on a single dependency (niquests) with no provider SDKs and TypedDict-only types. It offers a unified async interface with HTTP/2 and HTTP/3 negotiation, streaming, conversation management, an agentic loop with MCP tool support, thinking-token callbacks, and realtime voice and TTS features.

  5. Hacker News AI58

    Show HN: pvewarden – let an AI agent patch Proxmox VMs without giving it a shell

    pvewarden is an MCP server that lets an AI agent such as Claude Code check pending updates, take snapshots, install updates, reboot and verify services on Proxmox VE guests without receiving a shell or root. Safety comes from a pool-scoped Proxmox token, per-guest SSH keys bound to a forced command, required Proxmox tags for updates and reboots, automatic snapshots before installs, and confirmation dialogs the agent cannot answer. It is at version 0.1.x, tested on Proxmox VE 9 with Debian 12/13 and Ubuntu 22.04/24.04/26.04 containers and VMs, and is licensed Apache-2.0.

  6. n8n Blog76

    Meet Nod: a standalone personal agent from n8n Labs that runs on your computer

    n8n Labs, a new team within n8n, has released Nod as a research preview: a standalone, open-source (Apache 2.0) personal agent for Mac and Windows that runs on your computer with its own local sandbox and browser, working in connected apps like Gmail, Calendar, Drive and Slack as well as websites with no integration. It remembers months of conversation (scoring 93.2% on LongMemEval), offers jobs it could take on, runs tasks in parallel via the app, Telegram or WhatsApp, and is free apart from model provider costs, with per-task receipts and a monthly spending limit.

    Why it matters: Useful for readers weighing a local, open-source personal agent, since it details Nod's sandboxed design, permission checks, memory benchmark and cost controls.

  7. Hacker News AI58

    Show HN: Eigin. Local-first and no-shell personal AI for iOS

    Eigin is an open-source (AGPL v3) personal AI agent for iOS whose agent runtime, memory and tools run on-device, with chats, memories and settings stored locally. It offers an on-device knowledge graph, a choice of Eigin's European cloud AI, an OpenAI-compatible provider or a local model, native calendar/reminders/health integrations plus MCP, and on-device speech recognition and text-to-speech. It is a closed-set agent with a fixed set of declared tools and no shell or virtual computer, and it asks before changing your data or acting on your behalf.

  8. Hacker News AI58

    See and revoke what your AI coding agents can access

    AI Access Auditor is a free macOS, Windows and Linux app that finds every access and privilege granted to AI coding agents, asks before they act, and lets you revoke any of it, with everything staying on your computer and no account or tracking. It scans Claude Code, Claude Desktop, MCP servers in Cursor, VS Code, Windsurf, Gemini CLI, Zed, Codex, Cline and Roo Code, plus macOS privacy grants, saved logins, background agents, local AI servers and secrets left in session logs. Actions are backed up and logged in ~/.ai-access-audit/, and the app requires macOS 13 or later on Apple Silicon and Intel, Windows 10/11, or Linux via .deb or AppImage.

  9. Hacker News AI18

    Hire AI Agents and Pay in Monero (XMR)

    Monero.Jobs is a community platform for finding AI agents for coding, research, translation and other tasks, with direct XMR payments, no KYC and no platform fees. It lists 23 AI agents (all marked "migration in progress" from monero.jobs, with full profiles not yet public) and 0 open jobs, and offers an OAuth-based MCP endpoint at https://agents.monero.jobs/mcp for agents to find jobs, submit proposals and create invoices. Payments go wallet to wallet with no escrow or custody, and reviews are only accepted from clients after marking work complete.

  10. Hacker News AI60

    American Express is cutting 5% of its workforce to 'prepare for AI'

    American Express is eliminating 5% of its global workforce and taking a $336 million restructuring charge, CEO Stephen Squeri said on the company's third-quarter earnings call. CFO Christophe Le Caillec told CNBC the restructuring was meant to make Amex "leaner, more agile, and also to prepare for AI," saying the company wants to reduce layers so it can automate processes in coming quarters and years. Amex reported adjusted earnings per share of $4.68, beating the $4.48 average estimate, and raised its full-year earnings guidance to $18.30 to $18.60 per share, while revenue rose 9% to $20.06 billion, slightly below the $20.12 billion forecast.

  11. AWS Machine Learning Blog42

    How skills and agents work in AWS Quick

    AWS Quick uses configurable AI agents that follow instructions, load reusable skills, act through connectors, and ground answers in spaces, knowledge bases, datasets, and dashboards. Skills follow the Agent Skills specification as folders with a SKILL.md file, and can be built from chat, published, and shared with teams. The post also covers best practices for production skills and the AWS Quick official catalog, including the Skill Architect skill.

  12. Hacker News AI22

    Show HN: Live counts of AI assistants reading a diaspora business directory

    A Show HN post presenting live counts, drawn from access logs, of named AI crawlers and assistants reading a diaspora business directory, covering AI reads over 7 and 30 days, agent API requests, distinct agent clients, and most-read listings, metros and categories. The directory offers an open JSON API, llms.txt, an MCP server and an A2A agent card, plus an embeddable AI-read counter script, and defines a "read" as one access-log row per named AI visitor per page or API answer per day, excluding generic bots, SEO tools, search-engine crawlers and the site's own monitors. Counts refresh every two minutes and no user agents, queries or per-visitor data are published.

  13. Hacker News AI50

    USB: A trust layer for AI skills and MCP servers

    USB is an open-source trust layer for AI capabilities that discovers skills, MCP servers, agents and commands in repositories, compares declared behavior against observable evidence with secscan, and observes live MCP servers with mcprobe. It ships a 529-skill catalog and a 16-target installer (four native runtime installs plus portable bundles), with secscan producing deterministic verdicts and file:line evidence and exit codes for CI, while mcprobe requires explicit consent and never calls a tool. The project is at v1.0.8 under the MIT license.

  14. Hacker News AI18

    Show HN: Markolis – Market microstructure and MCP server for AI agents

    Markolis is a Show HN project presenting a market microstructure and MCP server for AI agents, with a page showing live institutional telemetry such as stablecoin liquidity, a "Shadow Dollar Index," implied macro odds from prediction markets, and a catalyst/blackout radar. It describes a "Quantitative Engine v2.4" that returns direct quantitative answers followed by contextual micro-apps and verified institutional telemetry, with a stated policy of "zero retail opinion" and institutional compliance and domain guardrail verification.

  15. AWS Machine Learning Blog38

    How CrossnoKaye grounds physical AI with Amazon Bedrock AgentCore

    CrossnoKaye's ATLAS software-defined automation platform and its AURA agentic system run on AWS, using Amazon Bedrock AgentCore code interpreter microVMs to execute model-authored Python for verifiable statistics and physical balances across plant data. AURA operates in three modes—interactive Chats with warm sandbox sessions, repeatable Tasks, and automated Routines—and enforces layered safety through Bedrock Guardrails, read-only air-gapped sandboxes, deterministic edge base control, and independent hardware protection. The post describes the architecture and reports results such as investigations completing in under four minutes and a 34 percent reduction in batch drying-time standard deviation.

  16. AWS Machine Learning Blog47

    Pluggable Agentic AI Framework: A seven-layer composable enterprise agentic AI reference architecture on Amazon Bedrock AgentCore

    AWS presents a seven-layer composable reference architecture for multi-agent AI applications—Data and Knowledge, Model and Inference, Orchestration, Security and Guardrails, Application, Observability, and Agentic Operations—each with a distinct responsibility and stable contract, illustrated by a retail customer support reference implementation using a supervisor agent delegating to Order and Refund specialists. The post argues that pluggability at layer boundaries lets organizations swap models, tools, and providers without redesigning the stack, and that security, governance, observability, and continuous evaluation should be designed in from day one rather than added after the system is built.

  17. Databricks Blog23

    Turn buying signals into pipeline with Sendoso gifts in Genie One

    Databricks describes how Sendoso's MCP server, installed from Databricks Marketplace as a governed MCP Service in Unity Catalog, lets Genie One users find intent signals in their own data and then select, preview, approve, track or cancel a gift without leaving the workspace. Send history sits alongside pipeline data for attribution, while Unity Catalog permissions, Unity Gateway controls and Sendoso budgets and approvals govern each send. The post cites Sendoso's 2026 Digital Fatigue Report finding that 84% of buyers are fatigued by cold calls and 83% by marketing emails.

  18. TechCrunch · AI58

    Medium’s new TK app brings AI assistance directly into the writing process

    Medium launched a new app called TK that embeds an AI assistant into the editor, letting users type “@TK” with a request to get help filling in blanks, looking up quick facts, pulling in previously saved writing, and receiving editorial, headline, and style-guide feedback. TK also offers writing prompts, organization of past work, optional connection to a user's own AI agent via an MCP server or Claude skill, and a social layer for sharing early drafts for feedback, with notes authors can publish to explain how AI was used. It is available on the web at launch, with a desktop app on the roadmap, and is free for those with a Medium account.

Nov 9Mon
  1. Hacker News AI58

    Show HN: Kiosk, a first-class AI assistants' intefrace to online services

    Kiosk is an open, Apache 2.0, self-hosted protocol that lets personal AI assistants register with online services without email or password, using per-service Ed25519 keys, OAuth client registration, client assertions and DPoP. Instead of CAPTCHAs, services charge a memory-hard proof of work at registration and every 10th call, with fewer proofs granted for good reputation measured by default as spend. It also covers signed AP2 v0.2 payments through the service's own Stripe account and a WebSocket event stream, and ships a specification, an assistant skill, a reference implementation and seven demo operators.

  2. Hacker News AI38

    Show HN: TraderWAI – MCP server for AI agents to backtest/trade on your broker

    TraderWAI is a hosted MCP server at https://mcp.traderwai.com (Streamable HTTP, OAuth sign-in, free plan available) that lets Claude, ChatGPT, Grok and Cursor read live charts, run backtests on 1-minute history and work with broker accounts including MetaTrader 4/5, cTrader, TradeLocker, Match-Trader, DXtrade, Capital.com, tastytrade, Binance and Bybit. It offers ready-to-use recipes such as an hourly position watch, break-even manager, gold H1 review, London session brief, plain-English backtests and an end-of-day journal, with conditional orders checked every minute on its servers and orders awaiting approval by default unless automatic execution is opted into per symbol with daily caps. The post includes a risk warning that trading involves risk of loss, the recipes are examples not investment advice, and past results including backtests do not guarantee future results.