- Claude can now connect to applications such as the concept, the Canva and the Strip
- AI can understand and help tasks using your actual work data
- Claude’s secure access reduces the need to constantly explain the context to AI
Anthropic has upgraded Claude with a new set of major tools which allowed the AI assistant to integrate directly into several popular software tools, including the concept, the canva, the band, figma, socket and prisma. The new directory of Claude tools means that you do not need to explain what you want to Claude each time you want to use these tools; Claude can now look at the same information as you to help you.
Until now, most AI interactions have required the copy and collage of each detail of your project management tool, explaining what is important, clarifying what each task means and double the verification that IA has understood. Now you can just ask him to do the task, and Claude will draw information directly from the relevant tool to manage things.
This may not seem revolutionary at first glance, but this context gap is the place where things are usually collapsed when you ask IA chatbots to help you. For example, if you work on a product launch in concept and you have a list of things to do, you should normally retype or download all the information on Claude. Now, once you have connected the concept to Claude, the AI can read the documents of your project directly and start assembling chronologies and presentation documents that correspond to the product because it sees what you see.
Or imagine a small business owner using Stripe to manage payments wishing a summary that customers paid last week and who always owe you for your services. Claude can now withdraw this data directly from Stripe with your permission. And with Canva, a virgin social media publication model can now be filled with a design and copy of Claude according to your memory. You describe what you need in clear language, and Claude will make something use.
Claude connected
These integrations are fueled by something called the context protocol of the model, or MCP. This essentially means that Claude can understand and act on the tools you use without the need for a whole tutorial. You simply connect an application once, and Claude gets secure access and limited to relevant information inside. It does not read your entire reception box or do not download your bank history, which is necessary to help you with the task to be accomplished.
You can access the claude tool directory and connect the applications you already use. If you are on a paid Claude plan, you will have access to distant application connections like Stripe and Concept. Office integrations, such as Figma and Socket, are available via the Claude Desktop application.
Other AI tools try something similar. Google Gemini appear in Docs and Gmail. Microsoft’s co -pilot is cooked in Word and Excel. But the taking of anthropic consists more in binding what you are already doing with AI, instead of cooking AI in these applications directly.
Of course, this does not make Claude Autonomé. He cannot pay your bills or manage your work entirely. And although Anthropic says that it is designed in mind with confidentiality and security, some are likely to be wary, even if you can choose what Claude can access. But for most regular users, this update represents something potentially very useful to stay informed of things. If, as Anthropic claims, it will save time and means that you do not have to redo a lot of tedious paperwork, it will probably be a very popular feature.
