Latest Tech News

Stay updated with the latest in technology, AI, cybersecurity, and more

Filtered by: mcp Clear Filter

Exposed MCP servers across the internet

Knostic’s research team conducted a systematic study to locate exposed MCP servers on the internet. Leveraging Shodan and custom Python tools, we fingerprinted and mapped production MCP servers. All servers we discovered were insecure and revealed their capabilities to anyone asking. In this series of posts, we are sharing our findings, along with a guide detailing how we fingerprinted MCP servers. We identified a total of 1,862 MCP servers exposed to the internet. From this set, we manually v

Exposing the Unseen: Mapping MCP Servers Across the Internet

Knostic’s research team conducted a systematic study to locate exposed MCP servers on the internet. Leveraging Shodan and custom Python tools, we fingerprinted and mapped production MCP servers. All servers we discovered were insecure and revealed their capabilities to anyone asking. In this series of posts, we are sharing our findings, along with a guide detailing how we fingerprinted MCP servers. We identified a total of 1,862 MCP servers exposed to the internet. From this set, we manually v

Claude AI now integrates with Canva

Anthropic's Claude can now create and edit designs with visual studio Canva from within an AI chat. This integration is powered by a Canva server that uses Anthropic's Model Context Protocol, or MCP. Claude can use Canvas's tools to generate a design or search for materials within a user's Canva workspace. This functionality requires a paid subscription to Claude, and access also varies based on the user's Canva plan. Multiple artificial intelligence platforms have started using MCP to connect

Anthropic’s Claude chatbot can now make and edit your Canva designs

Canva users can now create, edit, and manage their designs by describing their requirements to Anthropic’s Claude AI. The connection is the latest of several integrations that allow Claude users to access third-party tools and services, including Figma, Notion, Stripe, and Prisma, without having to leave their conversation with the AI chatbot. Starting today, Claude users will be able to use natural language prompts to complete design tasks in their linked Canva account, such as creating presen

Topics: ai canva claude mcp users

Understanding Tool Calling in LLMs – Step-by-Step with REST and Spring AI

✅ What Spring AI Handles for You ✅ Tool schema generation ✅ Argument binding ✅ tool_call_id mapping mapping ✅ Message state management ✅ Parallel tool orchestration ✅ Sequential tool routing ✅ Spring Boot DI, validation, and observability ✅ Compatible with OpenAI, Mistral, Gemini, and others You keep writing business logic. Spring AI wires up everything else. 🔌 Bonus: Tool Calling via MCP — No Extra Code Need your tools to work beyond just chat — like inside other agents or frontend c

Topics: ai mcp spring tool tools

Show HN: asyncmcp – Run MCP over async transport via AWS SNS+SQS

asyncmcp - Async transport layers for MCP Overview A regular MCP Server but working over queues : queue-based-mcp-example.mov Quoting from the official description : MCP is an open protocol that standardizes how applications provide context to LLMs. But a lot of this context is not always readily available and takes time for the applications to process - think batch processing APIs, webhooks or queues. In these cases with the current transport layers, the MCP server would have to expose

Show HN: MCP server for searching and downloading documents from Anna's Archive

Anna's Archive MCP Server An MCP server for searching and downloading documents from Anna's Archive Note Notwithstanding prevailing public sentiment regarding Anna's Archive, the platform serves as a comprehensive repository for automated retrieval of documents released under permissive licensing frameworks (including Creative Commons publications and public domain materials). This software does not endorse unauthorized acquisition of copyrighted content and should be regarded solely as a util

MCP isn’t KYC-ready: Why regulated sectors are wary of open agent exchanges

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now For something launched in November, the Model Context Protocol (MCP) has begun amassing a large number of users, all but guaranteeing the mass adoption needed to make it an industry standard. But there is a subset of enterprises that are not joining the hype for now: regulated industries, especially financial institutions. Banks and other

Supabase MCP can leak your entire SQL database

Model Context Protocol (MCP) has emerged as a standard way for LLMs to interact with external tools. While this unlocks new capabilities, it also introduces new risk surfaces. In this post, we show how an attacker can exploit Supabase’s MCP integration to leak a developer’s private SQL tables. The Problem LLMs are often used to process data according to pre-defined instructions. The system prompt, user instructions, and the data context is provided to the LLM as text. [ SYSTEM PROMPT ] You ar

Supabase MCP leaks your entire SQL Database, a lethal trifecta attack

Supabase MCP can leak your entire SQL database (via) Here's yet another example of a lethal trifecta attack, where an LLM system combines access to private data, exposure to potentially malicious instructions and a mechanism to communicate data back out to an attacker. In this case, General Analysis identify all three components in a single MCP - the Supabase MCP. They imagine a scenario where a developer asks Cursor, running the Supabase MCP, to "use cursor’s agent to list the latest support

tinymcp: Let LLMs control embedded devices via the Model Context Protocol

tinymcp Let LLMs control embedded devices via the Model Context Protocol. Warning tinymcp is an experimental project. Expect frequent breaking changes. Extreme caution should be taken when delegating physical capabilities to AI systems. Background The tinymcp project includes an MCP server, which is executed locally, but communicates with remote devices via the Golioth management API. It uses two existing device services on the Golioth platform, LightDB State and Remote Procedure Calls (RPCs

Tools: Code Is All You Need

Tools: Code Is All You Need If you've been following me on Twitter, you know I'm not a big fan of MCP right now. It's not that I dislike the idea; I just haven't found it to work as advertised. In my view, MCP suffers from two major flaws: It isn’t truly composable. Most composition happens through inference. It demands too much context. You must supply significant upfront input, and every tool invocation consumes even more context than simply writing and running code. A quick experiment make

MCP: An (Accidentally) Universal Plugin System

There's this thing about USB-C that nobody really talks about. Not the part where we all had to buy new dongles (RIP my dongle drawer, 2010-2023). The other part. See, we all thought USB-C was just going to be about charging things and moving files around like the other USBs. Very serious. Very purposeful. But because of the way it is it can do... other things. My friend Rex connected his toaster to his monitor last week. I don't know why. The toaster doesn't know why. But it worked, and now R

Topics: ai just like mcp protocol

MCP in LM Studio

LM Studio 0.3.17 introduces Model Context Protocol (MCP) support, allowing you to connect your favorite MCP servers to the app and use them with local models. LM Studio supports both local and remote MCP servers. You can add MCPs by editing the app's mcp.json file or via the new "Add to LM Studio" Button, when available. Also new in this release: Support for 11 new languages, thanks to our community localizers. LM Studio is now available in 33 languages. Many bug fixes, as well as improvemen

LM Studio is now an MCP Host

LM Studio 0.3.17 introduces Model Context Protocol (MCP) support, allowing you to connect your favorite MCP servers to the app and use them with local models. LM Studio supports both local and remote MCP servers. You can add MCPs by editing the app's mcp.json file or via the new "Add to LM Studio" Button, when available. Also new in this release: Support for 11 new languages, thanks to our community localizers. LM Studio is now available in 33 languages. Many bug fixes, as well as improvemen

MCP is eating the world

Despite the hype, Model Context Protocol (MCP) isn’t magic or revolutionary. But, it’s simple, well-timed, and well-executed. At Stainless, we’re betting it’s here to stay. “MCP helps you build agents and complex workflows on top of LLMs”. If you’ve paid attention, you know we’ve been here before. There are numerous past attempts at connecting the world to an LLM in a structured, automatic way. Function/tool calling : Write a JSON schema, the model picks a function. But you had to manually wir

Remote MCP Support in Claude Code

Today, we’re announcing support for remote MCP servers in Claude Code. Connect your favorite tools and data sources to personalize your coding experience without needing to manage local servers. Using Claude Code as your primary development interface Claude Code can access both tools and resources exposed by MCP servers, giving it the ability to pull context from your third-party services—such as dev tools, project management systems, and knowledge bases—and take actions within those services.

Show HN: EnrichMCP – A Python ORM for Agents

EnrichMCP The ORM for AI Agents - Turn your data model into a semantic MCP layer EnrichMCP is a Python framework that helps AI agents understand and navigate your data. Built on MCP (Model Context Protocol), it adds a semantic layer that turns your data model into typed, discoverable tools - like an ORM for AI. What is EnrichMCP? Think of it as SQLAlchemy for AI agents. EnrichMCP automatically: Generates typed tools from your data models from your data models Handles relationships between

Anthropic now lets developers use Claude Code with any remote MCP server

Sabrina Ortiz/ZDNET Anthropic pioneered the Model Context Protocol (MCP) open standard for connecting AI assistants and agents to data systems seamlessly and securely. Since MCP's introduction last year, the standard has become increasingly adopted across the industry, including by Microsoft, OpenAI, and Google. Now, the company is expanding capabilities for developers. Claude Code support for remote MCP On Wednesday, Anthropic announced that it would allow users to integrate Claude Code with

Asana warns MCP AI feature exposed customer data to other orgs

Work management platform Asana is warning users of its new Model Context Protocol (MCP) feature that a flaw in its implementation potentially led to data exposure from their instances to other users and vice versa. The data exposure was due to a logic flaw in the MCP system and not the result of a hack, but the risk that arises from the incident could still be significant in some cases. Asana is a project and task management SaaS platform used by organizations to plan, track, and manage work,