ScholarXIV

We will be showing great use cases of this MCP in the coming days. But before that, if you've got some incredible use cases for the MCP, comment it here and we'll give you ScholarXIV Plus for a month.

Introducing ScholarXIV MCP Your AI agent's new research backend We're very excited to launch the long awaited ScholarXIV MCP today. This MCP provides >30 tools and connects your AI agents and clients directly to ScholarXIV giving it access to our full suite of research tools. Features • Search papers by title, author, abstract, category, or keyword • Read full metadata and abstracts • Bookmark, like, and comment on papers • Create and manage paper collections • Browse and join public collections from other researchers • Create and manage your ScholarXIV Chats • and even run our deep research agents Easy Setup 1. A ScholarXIV account 2. An API key (get one here) 3. An MCP-compatible client 4. Copy & paste the client config 5. That's it! Works with all the major agents and IDEs like Codex, Claude, OpenCode, Cursor, Zed, VS Code, OpenClaw, Hermit, n8n and any MCP client. This MCP opens up the door for many more complex workflows and also your AI chats can finally be grounded in research instead of hallucinations. Check out the docs for detailed setup guides, example use cases and more. We can't wait to see all the epic ways you're going to use this. #Launch #ScholarXIVMCP #MCP @ScholarXIV

🥁🥁🥁

Something epic is launching today 👀

Two hours ago (June 22, 11:14 AM PT) we received an incident report stating our AI-Chat endpoint (powering our deep research agent) was down. Though you could run the research agent in chat, the health checking API returned an error. This was due to Vercel AI Gateway changing their server side API schema without prior notice. Which set off a schema validation error in our endpoints. But we were able to upgrade every dependency and flow related to this issue in one hour (June 23, 12:14 AM PT) and all systems are operational right now. Check status • status.scholarxiv.com Thank you! #Incident @ScholarXIV

OpenScholarXIV has been downloaded over 27,500 times and has been starred over 1,110 times. Thank you so much for the support - keep starring, contributing and sharing. #OpenScholarXIV #Stats @ScholarXIV

Using our Papers API you can access research papers upto 3x the limit of arXiv. This's great for any kind of product you can build with research papers - specially AI/agentic ones. #PapersAPI @ScholarXIV

Here's our blog post explaining why we built the Papers API and a brief overview of the process and how much better it is than anything else. Papers API • scholarxiv.com/blog/Introducing-Papers-API This's an overview of the problem and our solution, our engineering blog explaining how we did it will be published soon. Enjoy! #Blogs #PapersAPI @ScholarXIV

We can't wait to see what you're going to build with this. Impressive builds will always result in getting a free tier upgrade :) Send us your feedbacks, bug reports and builds at hello@scholarxiv.com and if you're facing any issues contact us at support@scholarxiv.com Have fun building!

ScholarXIV for Developers • scholarxiv.com/developers Alongside the Papers API we're also launching our developers platform. This's where you can manage your API keys, track usage, try the playground and explore the documentation. This's where every dev product we launch will be accessed and managed. The first dev product is our Papers API, coming soon is ScholarXIV MCP to give your agents powerful research capabilities, and then much more. #Launch #DevelopersPlatform @ScholarXIV

We hosted 3,032,697+ (3M+) papers so you don't have to explore research at the rate of one query per 3 seconds (arXiv's API limits) — instead you can explore research at 3,600 queries per hour. That's one query every single second, everyday! With that kind of rate you can imagine what kind of research agents and products you can build!

Introducing Papers API • scholarxiv.com/developers Papers API let's you search over 3 million research papers through a single API endpoint. Filter by title, author, category, abstract, or date. Get clean, structured metadata containing titles, authors, abstracts, categories, PDF links and more without parsing XML or rate-limiting yourself. What you get: • Simple search — query by keyword or title • Advanced search — filter by author, category, abstract, date, journal, report number, or arXiv ID • Clean JSON Response — includes titles, authors, abstracts, categories, PDF links, DOIs, and more • API key management — sign up, create a key, track usage and more • Free tier available — no credit card required Papers API is what ScholarXIV is built on top of and you can test it live in the playground without writing any code. Also check out our comprehensive documentation to get started. Can't wait to see what you're going to build with this! #Launch #PapersAPI @ScholarXIV

🥁🥁🥁

Something cool is launching tomorrow 👀

We've crossed over 800 users! Thank you! 🎉 #Stats @ScholarXIV

We have moved from incident.io to betterstack.com for our incident reporting! • status.scholarxiv.com The status page also reports more monitors; platform, API, AI-Chat, Sandboxes and Subscriptions with status history and chart. We've also made our health check API public for transparency! scholarxiv.com/api/health will respond with a comprehensive result! We've made this change to enable for more in-depth monitoring and incident reporting for our users and our on-call team! #Monitoring #Status @ScholarXIV

Claude Fable 5 is now available in ScholarXIV in our Pro package! Fable 5 is state-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, scientific research, and vision. But is also the most expensive model out there. If you're an AI researcher using Claude Fable 5 in ScholarXIV, you should know that when Fable 5 is used for frontier LLM development, the safe guards in the model limits the model’s capabilities through methods such as prompt modification, steering vectors, and PEFT and it does not notify the user. Anthropic estimated that this would affect approximately 0.03% of traffic. Try Anthropic's latest model in ScholarXIV.com #Models #ClaudeFable5 @ScholarXIV

There's also another good reason we've increased our pricing ...

We have updated our pricing to accommodate more usage and access to frontier models! We've been offering our launch pricing for a month now and been analyzing use of these models and we've decided the price change is justified. The Free package remains to be free with access to the same efficient models. While the Plus package is now $30/m with higher usage (with provider limits still in place) and the biggest change is our Pro plan which is now at $100/m but with access to every latest frontier model. Unlike traditional AI chat apps, ScholarXIV consumes much higher input tokens because it aggregates a lot of research as context. With simple queries reaching well over in the 100k-200k input tokens. This pricing change accommodates for that use. #Pricing @ScholarXIV

We've crossed over 700 users! Thank you! 🎉 #Stats @ScholarXIV