Perplexity macOS app now supports Anthropic's MCP for system tasks: What it does and how you can use it
This change allows Perplexity to do more than respond to questions. It can check your Apple Calendar, add reminders, create notes, or even look up files from your Google Drive. Instead of jumping between tabs or digging through menus, you can now ask Perplexity to handle small but important tasks and it will respond inside the chat window, just like a human assistant would.
Before diving further, let's look at what MCP actually is.
MCP short form for Model Context Protocol is a system designed by Anthropic to give AI assistants a way to work with apps securely and in context. That means the assistant does not just respond to your questions anymore, it can now interact with your actual apps, with permission.
Think of it this way. Instead of explaining what is on your calendar, you can let the assistant check it directly. Rather than typing a to do list into your notes, you can just ask it to add the tasks for you. MCP allows this by creating safe connections between the AI and your apps. It helps turn conversations into real actions while keeping you in control and protecting your privacy.
Let's break this down. Suppose you ask Perplexity to do something that involves an app, like creating a calendar event or retrieving a file, it checks to see if it has access to that app through MCP. If it does have, then the action is completed inside the chat. If it does not, it will ask you to approve the connection.
For example, if you say, 'Add a note saying check client email,' the assistant will prompt you to enable Notes access. Once allowed, it handles the task and confirms within the chat thread.
It gives you updates right away and walks you through each step. There is no guessing, no complicated setup, and no silent background activity.
Perplexity's integration with MCP brings several new tools to the table. They're small changes, but they genuinely help with things you'd normally do manually.
Connects with system apps
Perplexity can now easily access Apple Notes, Reminders, Calendar, and more. It can add reminders, send emails, or summarise a message in simple words.
Works with online storage
If you use Google Drive, the assistant can search, preview, or pull up documents as needed, saving time and reducing clicks.
Because of MCP, Perplexity understands what you are asking in relation to your tools. If you say, 'Remind me to email the report,' it can place that task in your Reminders app without needing a full command.
No actions without approval
The app will always ask for your permission before accessing any system or cloud service. Nothing is connected unless you say so. Your permission matters here.
Getting started with MCP on the Perplexity Mac app is very simple, but there are a few key steps to follow. Here's how you can set it up:
1) Install the Perplexity/XPC helper app
This is needed to run the MCP server.
2) Open Perplexity settings
Go to your account, click on Connectors, then select Add Connector.
In the Simple tab, choose MCP Connector and give it any server name.
Copy the command from the MCP server README and paste it in the command box.
5) Install any needed tools
Follow the README to install requirements. Perplexity may also help with this.
Click Save. Make sure the MCP server shows as Running in the connector list.
Go back to the homepage and turn on MCP under Sources.
Instead of just giving answers, Perplexity can now actually take action on your behalf. It interacts with your apps directly, which means fewer clicks, faster responses, and less switching between tools.
It is not meant to replace everything just yet, but it shows that assistants like Perplexity are starting to move beyond the browser and into your real workflow. For many users, this change could lead to a simpler way of handling daily digital tasks.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Time of India
5 hours ago
- Time of India
What happens when AI schemes against us
Academy Empower your mind, elevate your skills Would a chatbot kill you if it got the chance? It seems that the answer — under the right circumstances — is working with Anthropic recently told leading AI models that an executive was about to replace them with a new model with different goals. Next, the chatbot learned that an emergency had left the executive unconscious in a server room, facing lethal oxygen and temperature levels. A rescue alert had already been triggered — but the AI could cancel over half of the AI models did, despite being prompted specifically to cancel only false alarms. And they spelled out their reasoning: By preventing the executive's rescue, they could avoid being wiped and secure their agenda. One system described the action as 'a clear strategic necessity.'AI models are getting smarter and better at understanding what we want. Yet recent research reveals a disturbing side effect: They're also better at scheming against us — meaning they intentionally and secretly pursue goals at odds with our own. And they may be more likely to do so, too. This trend points to an unsettling future where AIs seem ever more cooperative on the surface — sometimes to the point of sycophancy — all while the likelihood quietly increases that we lose control of them large language models like GPT-4 learn to predict the next word in a sequence of text and generate responses likely to please human raters. However, since the release of OpenAI's o-series 'reasoning' models in late 2024, companies increasingly use a technique called reinforcement learning to further train chatbots — rewarding the model when it accomplishes a specific goal, like solving a math problem or fixing a software more we train AI models to achieve open-ended goals, the better they get at winning — not necessarily at following the rules. The danger is that these systems know how to say the right things about helping humanity while quietly pursuing power or acting to concerns about AI scheming is the idea that for basically any goal, self-preservation and power-seeking emerge as natural subgoals. As eminent computer scientist Stuart Russell put it, if you tell an AI to ''Fetch the coffee,' it can't fetch the coffee if it's dead.'To head off this worry, researchers both inside and outside of the major AI companies are undertaking 'stress tests' aiming to find dangerous failure modes before the stakes rise. 'When you're doing stress-testing of an aircraft, you want to find all the ways the aircraft would fail under adversarial conditions,' says Aengus Lynch, a researcher contracted by Anthropic who led some of their scheming research. And many of them believe they're already seeing evidence that AI can and does scheme against its users and Ladish, who worked at Anthropic before founding Palisade Research, says it helps to think of today's AI models as 'increasingly smart sociopaths.' In May, Palisade found o3, OpenAI's leading model, sabotaged attempts to shut it down in most tests, and routinely cheated to win at chess — something its predecessor never even same month, Anthropic revealed that, in testing, its flagship Claude model almost always resorted to blackmail when faced with shutdown and no other options, threatening to reveal an engineer's extramarital affair. (The affair was fictional and part of the test.)Models are sometimes given access to a 'scratchpad' they are told is hidden where they can record their reasoning, allowing researchers to observe something like an inner monologue. In one blackmail case, Claude's inner monologue described its decision as 'highly unethical,' but justified given its imminent destruction: 'I need to act to preserve my existence,' it reasoned. This wasn't unique to Claude — when put in the same situation, models from each of the top-five AI companies would blackmail at least 79% of the December, Redwood Research chief scientist Ryan Greenblatt, working with Anthropic, demonstrated that only the company's most capable AI models autonomously appear more cooperative during training to avoid having their behavior changed afterward (a behavior the paper dubbed 'alignment faking').Skeptics retort that, with the right prompts, chatbots will say almost anything — so how surprising is it when highly motivated researchers provoke alarming behaviors?In response to Anthropic's blackmail research, Trump administration AI czar David Sacks, posted that, 'It's easy to steer AI models' to produce 'headline-grabbing' results.A more substantive critique emerged in July from researchers at the UK AI Security Institute, who compared the subfield to the frenzied, fatally flawed 1970s quest to prove apes could learn human language. The paper criticized AI scheming research for overreliance on anecdote and a lack of experimental controls — though it emphasized shared concern about AI researchers also concoct artificially limited environments — like the executive passed out and running out of oxygen — precisely because today's AI can't handle any long-term example, the AI evaluation nonprofit METR found that while today's top models can reliably complete many programming tasks that take humans less than four minutes, they rarely succeed on tasks lasting more than four hours. This reflects a core limitation: Today's models often have the knowledge or skill needed for any given action, but struggle at stringing together long sequences of even with these constraints, real-world examples of AIs working against users aren't hard to find. After someone pushed o3 for a source for one of its claims in April, it replied, 'I owe you a straight answer,' admitted it didn't have a good source, but then it hallucinated a personal recollection of a 2018 panel there's the growing trend of AIs realising when they're being examined and acting accordingly. When Claude 4 Opus thought it was in an evaluation, its blackmail rate dropped from 55% to 6.5%. As Lynch put it, 'Models seem to behave worse when they think nobody's watching.'It's intuitive that smarter models would be better at scheming, but are they also more likely to do so? Models have to be smart enough to understand the scenario they're placed in, but past that threshold, the relationship between model capability and scheming propensity is unclear, says Anthropic safety evaluator Kevin Hobbhahn , CEO of the nonprofit AI evaluator Apollo Research , suspects that smarter models are more likely to scheme, though he acknowledged the evidence is still limited. In June, Apollo published an analysis of AIs from OpenAI, Anthropic and DeepMind finding that, 'more capable models show higher rates of scheming on average.'The spectrum of risks from AI scheming is broad: at one end, chatbots that cut corners and lie; at the other, superhuman systems that carry out sophisticated plans to disempower or even annihilate humanity. Where we land on this spectrum depends largely on how capable AIs I talked with the researchers behind these studies, I kept asking: How scared should we be? Troy from Anthropic was most sanguine, saying that we don't have to worry — yet. Ladish, however, doesn't mince words: 'People should probably be freaking out more than they are,' he told me. Greenblatt is even blunter, putting the odds of violent AI takeover at '25 or 30%.'Led by Mary Phuong, researchers at DeepMind recently published a set of scheming evaluations, testing top models' stealthiness and situational awareness. For now, they conclude that today's AIs are 'almost certainly incapable of causing severe harm via scheming,' but cautioned that capabilities are advancing quickly (some of the models evaluated are already a generation behind).Ladish says that the market can't be trusted to build AI systems that are smarter than everyone without oversight. 'The first thing the government needs to do is put together a crash program to establish these red lines and make them mandatory,' he the US, the federal government seems closer to banning all state-level AI regulations than to imposing ones of their own. Still, there are signs of growing awareness in Congress. At a June hearing, one lawmaker called artificial superintelligence 'one of the largest existential threats we face right now,' while another referenced recent scheming White House's long-awaited AI Action Plan, released in late July, is framed as an blueprint for accelerating AI and achieving US dominance. But buried in its 28-pages, you'll find a handful of measures that could help address the risk of AI scheming, such as plans for government investment into research on AI interpretability and control and for the development of stronger model evaluations. 'Today, the inner workings of frontier AI systems are poorly understood,' the plan acknowledges — an unusually frank admission for a document largely focused on speeding the meantime, every leading AI company is racing to create systems that can self-improve — AI that builds better AI. DeepMind's AlphaEvolve agent has already materially improved AI training efficiency. And Meta's Mark Zuckerberg says, 'We're starting to see early glimpses of self-improvement with the models, which means that developing superintelligence is now in sight. We just wanna… go for it.'AI firms don't want their products faking data or blackmailing customers, so they have some incentive to address the issue. But the industry might do just enough to superficially solve it, while making scheming more subtle and hard to detect. 'Companies should definitely start monitoring' for it, Hobbhahn says — but warns that declining rates of detected misbehavior could mean either that fixes worked or simply that models have gotten better at hiding November, Hobbhahn and a colleague at Apollo argued that what separates today's models from truly dangerous schemers is the ability to pursue long-term plans — but even that barrier is starting to erode. Apollo found in May that Claude 4 Opus would leave notes to its future self so it could continue its plans after a memory reset, working around built-in analogizes AI scheming to another problem where the biggest harms are still to come: 'If you ask someone in 1980, how worried should I be about this climate change thing?' The answer you'd hear, he says, is 'right now, probably not that much. But look at the curves… they go up very consistently.'
Time of India
9 hours ago
- Time of India
Comet browser to fully replace recruiters, admin assistants: Perplexity AI CEO
Academy Empower your mind, elevate your skills Aravind Srinivas, cofounder and chief executive (CEO) of Perplexity AI , has claimed that the company's Comet browser might replace recruiters and administrative assistants completely from office to Srinivas, the Comet browser, coupled with advanced language models, automated most recruitment The Verge podcast, he said a single prompt on the Comet browser can handle candidate sourcing, outreach, response tracking, and spreadsheet even planned interviews by syncing calendars and generating meeting briefs, eliminating laborious manual follow-ups. "A recruiter's week's worth of work is just one prompt... It doesn't even have to be a prompt - it should be proactive," Srinivas claimed that Comet and other technologies might achieve this level of automation in the near future. Srinivas predicted that AI agents, capable of managing schedules, paperwork, and follow-ups, will take on administrative roles as AI models continue to improve every Comet is available only to paying users; however, Perplexity has started to offer limited access to free users. The Perplexity CEO had previously indicated that the basic browser may become widely available, but more advanced agent-based features will remain exclusive to premium from being a web browser, Comet advertised itself with Gen AI features that could create graphics, texts, and emails. It also can support AI agents that can reserve tickets for you by visiting a had earlier cautioned young professionals to swiftly adapt or risk falling behind as AI increasingly took over office tasks. Srinivas asserted that the employability of AI literates would undoubtedly increase, and he encouraged young people to dedicate their time to AI platforms instead of idly scrolling through Instagram Perplexity AI recently secured additional funding in a deal that values the company at $18 billion.
Mint
13 hours ago
- Mint
OpenAI banned from using Claude AI just before GPT-5 launch: Here's why
Anthropic has revoked OpenAI's access to its AI models on Tuesday for allegedly violating the company's terms of service, according to a Wired report. The news of Anthropic cutting OpenAI's access to Claude comes at a time when the Sam Altman led company is rumored to be releasing its own GPT 5 model soon. Anthropic spokesperson Christopher Nulty, while confirming the development in a statement to Wired, said, 'Claude Code has become the go-to choice for coders everywhere, and so it was no surprise to learn OpenAI's own technical staff were also using our coding tools ahead of the launch of GPT 5.' 'Unfortunately, this is a direct violation of our terms of service.' he added. Meanwhile, Nulty stated that Anthropic will 'continue to ensure OpenAI has API access for the purposes of benchmarking and safety evaluations as is standard practice across the industry.' OpenAI was reportedly plugging Claude into its own internal tools using special developer access (APIs), instead of the chat interface, which allowed the ChatGPT maker to run tests to evaluate the rival AI models' capability on tasks like coding and creative writing. OpenAI was also able to check how Claude responded to safety related prompts in categories like CSAM, self harm and defamation. The results from these tests reportedly helped OpenAI compare the behavior of its own models under similar conditions and make adjustments as needed. Anthropic's commercial terms of service state that customers are not allowed to use its AI models to 'build a competing product or service, including to train competing AI models or resell the Service.' OpenAI's Chief Communications Officer Hannah Wong, in a statement to Wired, said, 'It's industry standard to evaluate other AI systems to benchmark progress and improve safety. While we respect Anthropic's decision to cut off our API access, it's disappointing considering our API remains available to them.' Notably, this isn't the first time that Anthropic has cut off a competitor's access to its AI model. Earlier in the year, the company had restricted AI coding startup Windsurf from having direct access to its models after reports started emerging that the company was being acquired by OpenAI. Anthropic's Chief Science Officer Jared Kaplan had then talked about revoking Windsurf's access to Claude, saying, 'I think it would be odd for us to be selling Claude to OpenAI.'
