AI Agent · Claude · TechCrunch AI
AI’s most important protocol is getting a little bit easier to apply
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
The Model Context Protocol (MCP) is one of the basic building blocks of AI interoperability, giving AI models a secure way to access external data sources and services.
Key facts
- Arcade raised $60 million in June based on the idea that most AI agents don’t fail because the underlying models are weak but because the infrastructure around them isn’t ready yet, and that’s
- The Model Context Protocol (MCP) is one of the basic building blocks of AI interoperability, giving AI models a secure way to access external data sources and services
- Sometimes the ID expires, so the client has to notice, request a new one, and carry on…
- Now every one of those machines has to know about a session ID that some other machine handed out
Summary
The official spec for the new version has been public since May, but they got an unusually clear explanation of the changes Monday morning from the folks at Arcade, a two-year-old startup that’s built its entire business around the work of getting AI agents to function inside real companies, letting them securely connect to and act on tools like Gmail, Slack, and Salesforce. Arcade raised $60 million in June based on the idea that most AI agents don’t fail because the underlying models are weak but because the infrastructure around them isn’t ready yet, and that’s what this update is trying to address. The first time an MCP client like Claude connects to a server, it sends a “hello”: the reporter is Claude, here’s their version, here are their capabilities. Picture a real deployment.