Latest news with #MCPServer
Yahoo
20 hours ago
- Business
- Yahoo
Varonis (VRNS) Unlocks Real-Time Data Security with AI-Powered MCP Server
Varonis Systems, Inc. (NASDAQ:VRNS) is one of . Varonis Systems, Inc. (NASDAQ:VRNS), a leader in data security and threat detection, has introduced the Varonis Model Context Protocol (MCP) Server, a new interface that allows customers to connect their preferred AI tools directly to the Varonis Data Security Platform. The innovation marks a significant step in enabling real-time, AI-driven access to enterprise data security operations. With the MCP Server, customers can use natural language prompts through AI clients such as ChatGPT, Claude, and GitHub Copilot to query data posture, trigger remediation, and streamline compliance tasks. The server enables users to carry out complex operations with simple instructions—for example, retrieving recent high-severity alerts, updating ServiceNow tickets, or running cleanup scripts to remove inactive guest accounts. A close up of a software engineer typing on a laptop keyboard, focusing on the code development part of the company. 'Automation is at the heart of everything we do,' said Yaki Faitelson, Co-Founder and CEO of Varonis. 'The Varonis MCP Server marks another leap forward in our agentic AI vision—giving customers access to Varonis' real-time data security insights and automated remediation from their own AI tools, IDEs, agent builders, and terminals.' By embedding Athena AI in its platform and supporting cross-platform automation, Varonis continues to expand its role in modern data protection. The MCP Server furthers the company's mission to deliver secure, intelligent infrastructure that helps organizations proactively defend sensitive information and reduce compliance burdens in complex cloud environments. While we acknowledge the potential of VRNS to grow, our conviction lies in the belief that some AI stocks hold greater promise for delivering higher returns and have limited downside risk. If you are looking for an AI stock that is more promising than VRNS and that has 100x upside potential, check out our report about this cheapest AI NEXT: 10 Best Small Cap Tech Stocks With Biggest Upside Potential and . Disclosure: None. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Mint
2 days ago
- Business
- Mint
Canva now works directly inside ChatGPT with new integration: How it works for users
Design platform Canva has announced two major product updates aimed at integrating its tools directly into artificial intelligence ecosystems. The company has rolled out a deep research connector for ChatGPT and introduced the Canva Model Context Protocol (MCP) Server, allowing AI assistants to access and generate designs using real-time user context. The deep research connector links Canva accounts with ChatGPT, enabling the AI assistant to pull from a user's existing design materials, such as presentations, brand documents, and reports. This allows for content analysis and generation within the same conversation, eliminating the need to switch between platforms or manually input references. This functionality targets professional users across industries. Marketers can extract messaging from campaign materials; business users can analyse planning documents; sales teams can prepare proposals using prior customer data; and educators can incorporate previous lesson content into new teaching material. In parallel, Canva has launched the MCP Server, a backend infrastructure that allows AI assistants to access a user's full design workspace, including templates, charts, and historical content. It supports features like generating on-brand visuals, resizing templates, importing PDFs via URL, and filling charts with formatted data generated by AI. These integrations are compatible with platforms including ChatGPT and Salesforce's Agentforce, with more expected to follow. According to the company, the tools are designed to operate within existing AI environments, turning Canva into a directly pluggable design component in broader digital workflows. The company said that the new features are secured under its internal AI safety framework, Canva Shield, which governs data access and privacy for users interacting with external AI tools. Notably, the launch comes as Canva continues to expand its AI offerings, which now include Canva AI, Canva Code, and AI-powered features in tools such as Canva Sheets.
National Post
3 days ago
- Business
- National Post
Treasure Data Launches MCP Server: Let Your LLM Talk to Your Data
Article content MOUNTAIN VIEW, Calif. — Treasure Data, the Intelligent Customer Data Platform (CDP) built for enterprise scale and powered by AI, has announced the release of its MCP Server, a new open-source connector that allows AI assistants like Claude, GitHub Copilot Chat, and Windsurf to interact directly with your Treasure Data environment. Article content Article content Powered by the open Model Context Protocol (MCP), this solution gives data teams a new superpower: the ability to explore and analyze customer data in an easy and effective way, using plain language and a conversation window. With the Treasure Data MCP Server, teams can query parent segments and segments, explore tables, and analyze data using natural language, making data insights more accessible than ever. Article content For years, data access has been bottlenecked by query languages, disconnected tools, and manual workflows. With its MCP Server, Treasure Data makes your CDP conversational, so users can ask real questions and get real answers, instantly. Article content 'This is the beginning of natural language analytics at scale,' said Rafa Flores, Chief Product Officer of Treasure Data. 'We're making it radically easier for teams to get value from their data without needing to write complex SQL or rely on someone else to do it for them. This is a major shift in how teams interact with data: Just you, your questions, and your AI.' Article content How it works Article content The MCP Server acts as a local bridge between your LLM-enabled tools and the Treasure Data platform. Once configured, it allows AI agents to securely interact with your CDP through structured tool calls. Whether you're exploring datasets, generating SQL queries, or switching databases, the assistant does the heavy lifting, you just describe what you want. Article content Users in Claude Desktop or GitHub Copilot in Visual Studio Code, for instance, might type: '@treasuredata Find the top 5 most viewed products in the past 7 days and show the revenue by region.' Article content Behind the scenes, your assistant connects through the MCP Server to Treasure Data, automatically generates the appropriate SQL, runs it, and returns the results, all within your chat interface. There's no tab switching, no query building, and no need to know SQL. Article content You can also ask the assistant to describe the schema of a table, switch databases, or even run more advanced analyses. For example: '@treasuredata In the 'www_access' table, find IP addresses that accessed more than 50 unique pages in under 10 minutes. Show me the first and last access time for each.' Article content Instead of spending an hour writing multi-step SQL and debugging joins, the AI does it for you, writing, refining, and executing the query directly within Treasure Data. The MCP Server handles the permissions, safely limits results, and ensures your API keys and environment variables are managed securely. Article content Accessible to data, marketing, and product teams Article content Accessible to any team, use cases of the MCP Server could include: Article content Marketing analysts quickly assessing campaign performance by region Data engineers validating new tables or run point-in-time quality assurance (QA) checks Product managers exploring user journey data and conversion funnels without needing help from a BI team AI developers chaining together multi-step queries to train models and test new hypotheses, all with natural language and zero SQL fluency required Article content By default, the MCP Server is read-only, making it safe for exploration. But advanced users can enable write access to support inserts and updates for more interactive workflows. Article content Why it matters Article content For most enterprises, the biggest barrier to using AI effectively isn't the model, it's the data. If an LLM can't access high-quality, governed data, it can't generate useful insights. Article content The Treasure Data MCP Server removes that barrier. The AI accesses the CDP directly, securely and intelligently, so teams can finally start having productive conversations with their customer data. Article content The MCP Server is available today in public preview on npm, and open for contributions and feedback on GitHub. Article content About Treasure Data Article content Article content Article content Article content Article content Article content
Business Wire
4 days ago
- Business
- Business Wire
Pictory Introduces One of the World's First AI Video MCP Servers
SEATTLE--(BUSINESS WIRE)-- Pictory, a leading provider of AI-powered video creation, today announced the launch of the Pictory MCP Server, a new lightweight integration layer that enables developers, AI assistants, and automation platforms to build intelligent video workflows with unprecedented ease and flexibility. 'Pictory's MCP Server eliminates the need for custom code and deeply technical integrations. Now, anyone can create professional, branded videos just by describing what they want.' Vikram Chalana, CEO at Pictory The Pictory MCP Server is fully compliant with the emerging Model Context Protocol (MCP), making it easy for clients like Claude Desktop, Cursor, and other automation tools to discover and orchestrate video creation capabilities through natural language. It exposes modular tools - such as create-storyboard and render-video - that handle the complexity of input validation, sequencing, and API orchestration behind the scenes. 'With the rise of AI assistants and agent-driven automation, we saw an opportunity to simplify access to our video creation API,' said Vikram Chalana, CEO at Pictory. 'The MCP Server eliminates the need for custom code and deeply technical integrations. Now, anyone can create professional, branded videos just by describing what they want.' The server empowers clients to dynamically compose workflows by chaining together high-level operations. For example, users can ask Claude to 'make personalized outreach videos for all healthcare customers in the midwest' and behind the scenes the client will extract a list of all customers from a CRM, like Hubspot, select a video template, generate a storyboard, apply a voiceover and branding, and render the final video - all through the simple natural language command. Designed for maximum flexibility, the MCP Server supports a tool-based architecture where each capability can be discovered and invoked individually. This modular approach gives AI assistants and developers full control over workflow composition without wrestling with API payloads. Setup is simple: developers configure their MCP client (e. g., Claude Desktop) with their Pictory API credentials and instantly gain access to the full range of video creation tools. Detailed instructions and configuration examples are available on the Pictory website. Looking ahead, Pictory plans to expand the MCP Server's capabilities to include video transcription, summarization, PowerPoint and PDF inputs, no-code integrations, and cloud-hosted deployment. About Pictory is an AI-powered platform that transforms scripts, blog posts, PowerPoints and other existing content into market-ready, professional-quality videos. With a mission to make video-creation, at scale, accessible to all, Pictory serves marketers, educators, and enterprise teams around the world.
Yahoo
19-06-2025
- Business
- Yahoo
Asana bug in new AI feature may have exposed data to other users for weeks
A bug in one of Asana's new AI features made user information accessible to other users for several weeks. The company said the issue was resolved and it was not the result of a malicious hack. Instead, it appeared to be a logic flaw in its MCP (Model Context Protocol) server that was released on May 1, according to cybersecurity firm UpGuard (via BleepingComputer). MCP is an open-source framework that enables AI assistants to interact with sites and apps. The introduction of Asana's MCP Server enabled companies to integrate AI features like summarization and natural language search from LLMs. SEE ALSO: 'Your Year in Asana' is a reminder of all the work you did (or didn't do) The rise of generative AI tools and new standards that enable interoperability for LLMs create new privacy issues and increased cybersecurity risk. MCP servers are a shiny new target for hackers, and there's also risk of prompt injection attacks, token theft, and a general increase in data leaks since MCPs request broad permission to function smoothly, according to a blog post from cybersecurity firm Pillar. According to UpGuard, the bug "appears to have been part of this initial release," and was discovered by Asana on June 4. But during this time, Asana users working with the MCP server have been able to access information from other accounts' "projects, teams, tasks, and other Asana objects," according to an email reportedly sent to customers impacted. In a statement to BleepingComputer, Asana said the bug impacted around 1,000 accounts. Asana has more than 130,000 companies using its project management platform, including some big companies like Uber, Spotify, and Airbnb. (Disclosure: Mashable's editorial team also uses Asana.) Asana took the server offline and informed customers using the MCP server on June 16 about the bug. "As soon as the vulnerability was discovered, our teams immediately took the MCP server down and resolved the issue in our code," Asana said in its statement to BleepingComputer. Meanwhile, the company sent a contact form to customers potentially impacted to compile a full report of which companies may have had their data exposed. It's unclear yet if there was any major data breach, but Asana advised companies to review their logs for MCP access and any information generated by their AI tools and report it to Asana if they find any data that doesn't belong to their company. UPDATE: Jun. 18, 2025, 1:50 p.m. EDT Asana confirmed in a status update that the affected server was back online as of June 17.
