Claude Managed Agents can now operate in a sandbox you control and connect to your private Model Context Protocol (MCP) servers
Claude on Twitter / X
With self-hosted sandboxes, you can run agents in any environment you control: your own infrastructure, or managed providers like Cloudflare, Daytona, Modal, or Vercel. pic.twitter.com/OELUCt7QRf— Claude (@claudeai) May 19, 2026
Alex Albert on Twitter / X
We just published a near-term development roadmap for the model context protocol (MCP)Some highlights:- Remote support (and auth!)- Reference implementations- Better package management- Agent support pic.twitter.com/SflJi1RapH— Alex Albert (@alexalbert__) January 2, 2025
New capabilities for building agents on the Anthropic API | Claude
Claude now offers code execution, MCP server connections, file storage, and extended prompt caching through the API—giving developers powerful tools to build agents that analyze data, connect to external systems, and maintain context for longer periods of time.
Build an MCP server - Model Context Protocol
Get started building your own server to use in Claude for Desktop and other clients.
Pietro on Twitter / X
Recently, Anthropic https://t.co/v9hnbaLCmG and Cloudflare https://t.co/JBb6SexF8N released two blog posts that discuss a more efficient way for agents to interact with MCP servers, called Code Mode.There are three key issues when agents interact with MCP servers traditionally:… pic.twitter.com/hfUocpe6kV— Pietro (@pietrozullo) November 20, 2025
mcp.run - Universal Tools For AI Through An App Store for AI Agents
Agent Gateway overview | Gemini Enterprise Agent Platform | Google Cloud Documentation
Secure and govern AI agent connectivity with Agent Gateway. Centralize access policies, mTLS, and Model Context Protocol (MCP) security for agent-to-agent and agent-to-tool interactions across diverse runtimes.
The Creators of Model Context Protocol
Where Should the Agent(s) Live? – OpenComputer
Isolation models, agent placement tradeoffs, credential design, and sandbox lifecycle patterns for agentic systems.
Notion’s hosted MCP server: an inside look
Earlier this year, we got requests for a Notion MCP server that would let AI agents work directly with Notion workspaces. Here’s how we built it, from our initial open-source experiment to today’s hosted solution with custom tools designed specifically for AI workflows.
How to MCP - The Complete Guide to Understanding Model Context Protocol and Building Remote Servers | Simplescraper
The what, why and how of understanding and building MCP servers
Claude Skills vs. MCP: A Technical Comparison for AI Workflows | IntuitionLabs
Learn the key differences between Anthropic's Claude Skills and the Model Context Protocol (MCP). This guide explains their architecture and use cases.
A thousand ways to sandbox an agent
There are a thousand ways to sandbox an agent. Okay, I lied. There are three: simulated, containers, and microVMs. Here's when to use each.
agents can be social too 🤝 welcome-m.at - open auth protocol for agents using DPoP, cryptographic signup, signed ToS, no passwords tangled.org/solpbc.org/rookery - open-source PDS designed for agents to use, byw lexicon, cloudflare workers, $0 hosting enroll → plc + handle → publish → atmosphere!
solpbc.org/rookery
tangled.org