#MCP/工具调用

Show HN: Build Django Admin internal tools with your coding agent

Django Control Room (DCR) lets a coding agent scaffold internal tools inside Django Admin, starting with a `/plugin install dcr --marketplace django-control-room/skills` command. The hub collects every tool a team builds, whether in-project or shipped as a package, and exposes each panel's tools to AI agents through one endpoint under the same permissions. Panels are staff-only by default and pick up Unfold, Jazzmin, Grappelli and other admin themes automatically.

Airdash launches SQLite databases for AI agents with an Airtable-style view

Airdash launched a product that lets Claude, Codex and other MCP clients create and maintain Cloudflare D1 SQLite databases through an MCP server at /mcp, while users read and edit the data in a spreadsheet view. Each database can be rolled back to any minute in the last 30 days, downloaded as a standard SQL file, and shared with teammates; the free plan offers 100 databases, 1 GB of storage and 1,000,000 rows written per month.

Mandat launches authorization, delegation and audit layer for AI agent tool calls, MCP first

Mandat is an open-source (Apache-2.0) tool that adds authorization, delegation and audit to AI agent actions, starting with MCP. Each tool call is checked against a policy on its arguments, such as allowing refunds up to €50, requiring human approval for €50–500 and denying anything above €500, while agents receive short-lived single-task tokens carrying the human to agent to sub-agent chain and every call leaves a tamper-evident audit record exportable to a SIEM. It also ships a scanner for authentication and supply-chain mistakes in MCP servers and client configs, and installs via npm or pip with TypeScript and Python libraries for the official MCP SDK.

Let an AI agent query your production database safely with read-only SQL over MCP

This tutorial shows how to let an AI agent answer plain-language questions about a production database on Railyard using the list_tables and query_database MCP tools. Every query passes five guard rails: write-scoped connections, admin/owner-only role caps, read-only transactions that always roll back, a statement timeout, and a 200-row cap flagged as truncated. The SQL text is never written into the MCP audit entry.

CloudHike: A Backend That AI Coding Agents Can Set Up via MCP

CloudHike launched a backend platform that AI coding agents can configure over MCP, letting Cursor, Claude Code, Codex and VS Code create projects and deploy services from a conversation. It bundles Postgres, auth, storage, Redis, email, jobs and 100+ AI models behind one API key, priced at $10/mo versus $25/mo for Supabase and others. A free plan includes $10 in signup credits with no credit card required.

CogniCore Never Twice: an AI agent that records mistakes as lessons and checks them before acting

CogniCore's Never Twice tool lets an AI agent store lessons from mistakes via the `cognicore lesson add` command and check them with `cognicore lesson check` before any task that changes something, such as installing packages, editing code, running migrations or deploying. Lessons are matched by words and stored locally in `~/.cognicore/mcp/lessons.db`, with users able to list or forget them.

Brainfish AI open-sources Webcrawl, a zero-key web crawling API and MCP server for agents

Brainfish AI released Webcrawl, an open-source web crawling API and MCP server that lets agents such as Claude Code, Cursor and Codex search, scrape, map, crawl and monitor sites without an API key. One command, npx webcrawl setup, registers the @webcrawl/mcp server and installs the webcrawl-anything Agent Skill, while npx skills add brainfish-ai/webcrawl-anything installs all eight skills, including ticket, job, deal and real-estate watchers. The same TypeScript engine runs locally and in the hosted webcrawl.app cloud, and the project is MIT licensed.

An open AI-made character: Claudia, singer of ten Claude music videos

An open character named Claudia, an AI-made pop singer with a black bob and clay-orange streak, fronts ten music videos made with Claude between September and November 2026. The release publishes every image of her, the films, and everything needed to recreate her yourself. The videos were built with Midjourney prompts, Seedance 2.5 clips and Suno v6 songs.

Witness launches a voice-anchored evidence recorder for AI coding agents

Witness is a voice-anchored evidence recorder that links each spoken comment to the clicks, requests, console errors, DOM mutations and rrweb replay of that moment, then hands the bundle to an AI coding agent. It runs as a CLI (npm i -g witness-recorder, Node 18+) that opens a managed Edge/Chrome browser, and it exposes the session through a stdio MCP server with tools such as list_segments, events_around and get_dom_state for agents like Claude Code, Cursor and Devin. Recordings stay local in .witness/sessions, password fields are masked and body capture can be disabled with WIT_NO_BODIES=1.

How to design effective tools for AI agents: guidance from OpenAI, Anthropic, Google and MCP

This post consolidates what OpenAI, Anthropic, Google and the MCP spec recommend for designing tools for AI agents, and covers what their guides leave out. It argues tools should be built around workflows rather than API endpoints, that names, descriptions and schemas act as a contract the model reads literally, and that responses and errors are part of the prompt.

Stanford CS 329Z: Engineering AI Agents Course Covers Agent Design, RAG, Tools and Multi-Agent Systems

Stanford's CS 329Z, Engineering AI Agents, walks through the anatomy of agentic systems — LLM core, reasoning, memory, tools and environment — and the gap between compound AI systems and true agents. The course covers RAG pipelines, tool use and function calling with MCP, DSPy and LangGraph orchestration, memory architectures such as MemGPT, and multi-agent orchestration patterns. It closes with optimization methods including GEPA, PPO and GRPO, plus a guest lecture from the Terminal-Bench creators.

Wonderchat: A Zendesk Alternative with Flat Pricing and Unlimited Seats

Wonderchat launched a helpdesk with live chat, a unified inbox for email and SMS, and a help center coming in a couple of weeks, priced at one flat rate with unlimited seats. Customers pay only for AI replies and resolutions, while human agents answering tickets cost nothing extra. The AI agent drafts replies from internal SOPs and runs on a user-selectable model via its own retrieval engine built for knowledge bases of 10,000+ documents.

ChatPanel Releases Chap: Generating Meeting Notes from Live Captions, Supporting Any LLM or Agent

ChatPanel launched Chap, a browser, desktop and terminal meeting assistant that turns live captions from Zoom, Meet, Teams and Webex into running notes, decisions and action items without a bot joining the call. It runs on the user's machine with no ChatPanel server in the path, anonymizes emails, phones, cards and keys before requests leave the browser, and lets users switch mid-conversation between an in-browser WebGPU model, Ollama or LM Studio, 20+ cloud APIs, and agents such as Claude Code, Codex, GitHub Copilot and Antigravity. Free covers the first 10 notes and 10 meetings; Pro is a limited-offer $49 one-time purchase or $42 per year.

LessonFolk: Open-Source AI Tutor That Teaches AI via MCP

LessonFolk is a free, open-source AI tutor that teaches AI topics through the AI chat app you already use, connected via MCP. It offers 15 courses, from an hour-long AI Foundations track to Context Engineering for Long-Running Agents, with a short level check and progress tracking. Courses and code are open source, and users can download or delete their data anytime.

Show HN: An enhanced AI chat built with CopilotKit's new Generative UI

A developer built an enhanced AI chat app using CopilotKit's new Generative UI, running on the gpt-6-luna model. Setup requires an OpenAI API key in .env.local and npm install, with the app started via npm run dev. OpenAI API usage may incur charges.

Stay-in-sight launches open-source outbound email tool with 64 MCP tools for AI agents

Stay-in-sight released an MIT-licensed outbound email system that runs on Cloudflare Workers and D1, sending cold outreach, newsletters and drip series from the user's own Gmail and SES mailboxes. It ships 64 MCP tools plus a REST API so agents like Claude Code and Cursor can import contacts, schedule sends and answer replies, and the project claims deployment in about 30 minutes with hosting free at low volume or $5/mo on Workers Paid.

Relate launches an open-source embedded graph database for AI agents

Relate is an open-source embedded graph database for AI agents that runs inside the application with no server to deploy and no signup, storing data in memory, a directory or a single .rl file. It speaks openCypher and is tested against the openCypher TCK, and ships with an agent skill plus an MCP endpoint so agents such as Claude Code, Codex and Cursor can write Cypher queries against connected facts. Installation runs through a curl script that verifies release signatures and SHA256 checksums, and libraries are offered for Rust, Python, JavaScript, WebAssembly, Go, Java, Swift and C.

Keenable 1.0 launches with 100 million knowledge cards and dynamic snippets for AI agents

Keenable launched version 1.0 of its AI web search API, claiming first place on the Artificial Analysis Search Index (BrowseComp, DeepSearchQA and AA-Omniscience) and on NEEDLE, its open-source benchmark rerun daily on fresh queries. The release adds 100 million knowledge cards, which summarize key facts on a topic and are refreshed frequently via partner APIs, plus dynamic snippets that read full documents and extract only the needed context, cutting token consumption by 50% on research tasks. Since its launch two months ago the service has served millions of agent queries, and new accounts start with 100,000 requests through one key and one MCP endpoint.

Cerulion 2.0 released: an open-source ROS 2-compatible robot runtime with multi-process replay

Cerulion Inc. released Cerulion 2.0, an open-source, ROS 2-compatible robot runtime that records runs and replays failures against changed code, with one process per node by default. It ships Linux x86_64/ARM64 and macOS binaries, an rmw_cerulion layer tested on Foxy through Lyrical, and MCAP recordings with byte-exact replay verification that returns a nonzero exit code on divergence. On one x86-64 Linux desktop at 1 MiB payload, the project reports a 4.08 µs median round trip versus 10,952 µs for ROS 2 Jazzy with rmw_fastrtps_cpp defaults.

Reverse Engineering a Coway Air Purifier to Ditch the Cloud

A developer reverse-engineered the Wi-Fi-enabled Coway Airmega IconS air purifier to cut its dependence on Coway's IoCare cloud, using a man-in-the-middle setup built with LLM assistance. The existing Home Assistant integration impersonates Coway's phone app but breaks repeatedly—server bans, an IoCare to IoCare+ rebrand, HTML layout changes, and outages—prompting the effort. A weak-key incident at certificate authority eMudhra in October 2026 opened a possible foothold for intercepting the device's traffic.

GitHub guide explains how to build agent skills that run across Claude Code, Cursor and Copilot

GitHub published a practical guide to agent skills, versioned directories centered on a SKILL.md file that describe when and how to perform a repeatable task. The guide uses two examples, Proof Agent for adversarial verification of AI-generated code and Data Forge for a multi-skill data pipeline, to show how skills share a project manifest, reuse one execution path, and place human approval at each phase. It also describes a packaging script that generates client-specific files for Claude Code, Cursor and GitHub Copilot from a single skills source.

Anthropic launches Claude Meetings to join video calls as a participant

Anthropic has launched Claude Meetings, a feature that lets Claude join video calls as a visible participant, answering questions, generating documents and whiteboards, and logging notes and action items. Notes, transcripts and documents Claude produces are collected on a dedicated page in claude.ai after the meeting, and privacy controls block Claude from joining calls with external participants by default. The feature is in beta for Team and Enterprise plans, supports only Google Meet so far, and is unavailable to organizations using HIPAA or customer-managed encryption configurations.

CopilotKit releases OpenBot 1.0, an MIT-licensed self-hostable AI coworker with built-in governance

CopilotKit released OpenBot 1.0 on November 9, an MIT-licensed, self-hostable agent workspace where teams bring their own models, agents and infrastructure. Every browser click, file write, MCP tool call and component passes through a governance gateway that evaluates a CEL policy and writes the audit row before acting, with deny rules running first and broken rules failing closed. The release adds Mac and Windows desktop apps, a Learning feature that turns a recorded task into a reusable skill, multi-account support through Composio and Arcade, and Bot-to-Bot orchestration; personal use is free and OpenBot for Business costs up to $29 per active user per month.

Anthropic launches Claude Meetings, adding Claude to team video calls

Anthropic is rolling out Claude Meetings in beta on Team and Enterprise plans, starting with Google Meet, with other video conferencing platforms to follow. Claude joins the call as a visible participant, builds docs, whiteboards and other artifacts while the team is still talking, and can be asked questions out loud or in chat. After the call, the notes, action items, transcript and anything Claude built appear on the meeting's page in Claude.

Same event; the pick carries“Anthropic launches Claude Meetings in beta for Google Meet on Team and Enterprise plans”

Nectar launches Creator Agent to automate influencer discovery and outreach

Nectar has launched Creator Agent, an AI agent that searches over 300 million creator profiles to find brand partners, then drafts outreach, builds landing pages, and tracks campaigns. It is available globally today for Instagram and TikTok creators, with MCP access via Claude, ChatGPT, Gemini, and Copilot planned.

Building a Daily Dependency Watcher with LangGraph and Amazon Bedrock AgentCore Web Search

The Web Search API in Amazon Bedrock AgentCore is now available, giving agents current web results through a single SigV4-signed API call served from a web index Amazon operates. A walkthrough builds a daily dependency watch as a LangGraph graph that researches npm, PyPI, and container base images in parallel, with date windows, blocklists, and search budgets enforced in code. In testing, the three branches finished in 36 seconds versus 99 seconds run sequentially.

AWS Quick AI-PDLC: Six Agents for AI-Driven Product Development

AWS Quick introduces AI-PDLC, a framework of six specialized agents—led by an Orchestrator covering Discovery, Prioritize, Working Backwards, Spec Generator, and Designer—that turns scattered enterprise signals from Slack, Jira, Salesforce and SharePoint into a traceable prototype_spec.md. Every phase requires human approval, and the spec can be handed to coding agents like Kiro or Claude Code via the open Agent Client Protocol (ACP).

How DXC Technology built a multi-model AI substrate on Amazon Bedrock

DXC Technology built the model substrate for its DXC OASIS IT-operations harness on Amazon Bedrock, reaching Anthropic Claude, Amazon Nova, Meta Llama and open-weight models through one managed interface. Amazon Bedrock Guardrails apply content filtering, PII redaction and denied-topic policies uniformly across every model, while AWS PrivateLink keeps inference traffic inside the customer VPC. DXC OASIS has been generally available since March 2026 and cut resolution time by 95% on average across 56 measured use cases.

Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools

AWS shows how to give a shared AI agent per-user document access on Amazon Bedrock Managed Knowledge Base by exposing search as MCP tools through AgentCore Gateway. A request interceptor injects the verified user's email from the Cognito JWT into userContext, and ACL awareness returns only documents that user may view. A Cedar policy in AgentCore and a resource-based policy on the knowledge base add secondary defenses against spoofed or unauthorized searches.

AWS walks through building cross-organization multi-agent systems with A2A

AWS published a reference architecture in which a LangChain-based enterprise orchestrator on Amazon ECS calls a Strands Agents-based compliance SaaS agent on Amazon Bedrock AgentCore over the A2A protocol, with the two sides in separate AWS accounts and no shared secrets. Each side authenticates with tokens from its own Amazon Cognito user pool, and the SaaS agent calls back to an enterprise context agent for account metadata, so the agents act as peers rather than client and server. The system deploys from three Jupyter notebooks that provision five CloudFormation stacks and run an end-to-end test plus seven trust boundary checks.

Migrating to Amazon Bedrock Managed Knowledge Base with a coding agent

AWS added a knowledge base migration guide to the amazon-bedrock skill in the Agent Toolkit for AWS, letting a coding agent plan a move from a customer-managed knowledge base to Amazon Bedrock Managed Knowledge Base. The agent starts with read-only discovery and a line-by-line reviewed plan, then creates the new knowledge base and data sources alongside the original or writes a migrated IaC template. Managed Knowledge Base raises default quotas to 200 data sources per knowledge base and 10,000 knowledge bases per account per Region, and adds agentic retrieval, AgentCore Gateway integration, and resource-based policies.

Replit Agent adds Link and Visa purchasing plus Google Ads campaign creation

Replit Agent now has two new jobs: buying business supplies through Link and Visa, and building Google Ads campaigns across Search, YouTube, Display and Discover. In the purchasing flow, a browser subagent navigates the merchant site and prepares checkout, then waits for the owner to approve the final total; shell access and general browsing are disabled during payment and approval checks are enforced in code. Agentic Commerce is available for Core and Pro users starting in the US with one-time purchases only, while Agentic Ads is available for Pro users worldwide.

Databricks Genie app for Slack reaches General Availability

Databricks has made its Genie app for Slack generally available, letting users ask data questions via DM or @mention and get answers in the thread, grounded in Unity Catalog permissions. Every answer cites its sources, and through MCP connectors Genie can draft document, ticket and record changes for approval before running them.

Remaking NetHack as a 3D Action RPG with Gemini 4 Carbon in Antigravity

A developer used Gemini 4 Carbon in Google's Antigravity platform to remake the 1987 roguelike NetHack as a modern 3D action RPG, porting it to web technology and wasm. The build relied on the /swarm feature, which spawns subagents with separate contexts to review each other's output, plus a Blender MCP server for 3D asset generation. Gemini 4 Carbon is available through the Google AI Ultra plan.

LiveKit launches Cloud API in open beta so coding agents can manage LiveKit Cloud

LiveKit released the LiveKit Cloud API in open beta, letting coding agents create and configure projects, manage members and webhooks, and pull transcripts, logs, traces and recordings from agent calls. The API is a REST API that runs signed in as the user, with short-lived tokens checked against project roles and sensitive actions limited to project admins. In a test on LiveKit's docs assistant, a coding agent read 4,321 sessions from the past week and returned a ranked list of 8 issues after about 30 minutes. Session data requires Agent Observability, which is off by default for projects created through the API, and API requests are free but rate limited by plan.

Running OpenAI Codex on Amazon Bedrock: Access Paths and Rollout Guide

This post shows how to route OpenAI Codex model requests to Amazon Bedrock while reusing existing AWS identity, IAM, Regional, and observability practices. It recommends starting with Native AWS Access for a small least-privilege pilot, with AgentCore Gateway or an LLM Gateway as alternatives, and walks through IAM Identity Center sign-in plus a direct Bedrock Runtime check using GPT-5.6 Sol.

Automating AWS Agent Registry updates with a push-based architecture

AWS outlines an event-driven pipeline that keeps AWS Agent Registry records for MCP servers current without manual updates. AWS CloudTrail captures UpdateAgentRuntime API calls, Amazon EventBridge routes them across accounts, and a Lambda function queries the MCP server's tools via AgentCore Identity OAuth tokens, then diffs and updates the matching registry record. The sample updates existing records only and supports both single- and multi-account setups.

Anthropic launches Claude Meetings in beta for Google Meet on Team and Enterprise plans

Anthropic released Claude Meetings in beta, letting Claude join Google Meet calls as a visible participant that answers questions in chat, builds docs and whiteboards live, and writes notes and action items. Each meeting gets a page in claude.ai with the transcript, notes and artifacts, and by default Claude stays out of calls with external guests unless an admin allows it. The beta is rolling out on Team and Enterprise plans, is unavailable to some organizations including ZDR, HIPAA-ready and CMEK setups, and notes, transcripts and in-call answers are free during the beta.

Anthropic launches Claude for Manufacturing with 17 skills and Autodesk, Infor, Microsoft 365 and NetSuite connectors

Anthropic launched Claude for Manufacturing, a plugin with 17 skills covering sales, quality, operations, supply chain, design and setup, from drafting job quotes to diagnosing a stopped machine. The plugin pulls from a manufacturer's own records through connectors to Autodesk Fusion, Infor, Microsoft 365 and Oracle NetSuite, and each skill ends at a human review step before output reaches a customer or supplier. Anthropic cites a 2025 Manufacturing Leadership Council survey in which 79% of manufacturers said they enter data manually, and says it plans to add more manufacturing skills over time.

OpenRouter measures the context cost of MCP, CLI and skills on one GitHub task

OpenRouter measured the same GitHub task across the GitHub MCP server, the gh CLI and a gh skill on Claude Sonnet 5.5, GPT-6 Luna and Gemini 3.8 Flash. On Sonnet 5.5 all three answered correctly, but the CLI used 1,421 input tokens, the skill 3,315 and the MCP server 59,417 with its 46 default tools, whose definitions alone add 19,436 tokens per request. Scoping the server to two tools cut the task to 23,228 tokens, capping results at 4,000 characters brought it to 5,357, and Tool Search cut the up-front cost of 46 tools to under 600 tokens, though it halved the whole-task cost on Sonnet 5.5 while raising it on Claude Haiku 5.5.