Anthropic shared a post on May 23, 2025, on X (previously Twitter) and announced four new features now available in public beta on the Anthropic API. These features can help developers to build more “powerful AI agents.” The new features include a code execution tool, an MCP connector, a Files API, and extended prompt caching. Each one brings improvements to how developers can use Claude for tasks. The code execution tool enables Claude to act as data analyst to run Python code, create visualisations, and analyse data during API calls. The MCP connector will allow easy connection to remote MCP servers without writing client code, handling tool discovery and errors automatically. The Files API will let users to upload documents once and reuse them across conversations and streamlining workflows. Extended prompt caching now offers a 1-hour TTL, which reduces costs by up to 90% and latency by up to 85%, to improve long-prompt efficiency. Anthropic Introduces Next-Gen AI Models Claude Opus 4 and Claude Sonnet 4, Advancing With Coding and Reasoning Capabilities.

Anthropic Announces New Features on API

Today, we're announcing four new capabilities on the Anthropic API to help developers build more powerful AI agents.

A code execution tool, MCP connector, Files API, and extended prompt caching: pic.twitter.com/Ie9EcOrf0M

— Anthropic (@AnthropicAI) May 22, 2025

(SocialLY brings you all the latest breaking news, viral trends and information from social media world, including Twitter (X), Instagram and Youtube. The above post is embeded directly from the user's social media account and LatestLY Staff may not have modified or edited the content body. The views and facts appearing in the social media post do not reflect the opinions of LatestLY, also LatestLY does not assume any responsibility or liability for the same.)