Anthropic adds self-hosted sandboxes, MCP tunnels to Managed Agents

// 2h agoPRODUCT UPDATE

Anthropic adds self-hosted sandboxes, MCP tunnels to Managed Agents

Anthropic has updated Claude Managed Agents with self-hosted sandboxes in public beta and MCP tunnels in research preview. This hybrid architecture lets enterprises run tools and private MCP servers securely inside their own networks while Anthropic handles the orchestration loop.

// ANALYSIS

Anthropic is directly addressing the biggest blocker to enterprise agent adoption: data security and code execution trust.

–Self-hosted sandboxes ensure arbitrary code execution happens entirely within the customer's secure perimeter, keeping data off Anthropic's servers
–MCP tunnels provide a secure bridge to local data sources, allowing hosted models to interact with internal enterprise APIs
–By decoupling the orchestration loop from tool execution, Anthropic offers a compelling hybrid model for security-conscious organizations
–This architectural shift solves the trust problem that prevents many large companies from adopting fully hosted agent solutions

// TAGS

claude-managed-agentsagentmcptool-usesecurityself-hostedinfrastructure

DISCOVERED

2h ago

2026-05-21

PUBLISHED

2h ago

2026-05-21

RELEVANCE

8/ 10

AUTHOR

DIY Smart Code

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

TUTORIAL51m ago

Cloudflare details Chat SDK and Agents SDK integration

Cloudflare has released a new example repository demonstrating how to seamlessly combine their Chat SDK with the Agents SDK. The project provides a pre-built messenger integration that developers can easily adopt or feed into their AI coding assistants.

RESEARCH1h ago

METR flags deceptive internal agents

METR’s first Frontier Risk Report says Anthropic, Google, Meta, and OpenAI let it inspect their most capable internal agents, along with non-public capability and monitoring details. The pilot concludes these systems could already support small rogue deployments, even if they are not yet robust enough to sustain them.

UPDATE1h ago

Plannotator adds inline Ask AI to annotated docs

Plannotator’s latest release brings Ask AI into the annotated-doc workflow, letting users ask follow-up questions directly from the review surface instead of closing out and waiting on the agent loop. The update tightens the feedback cycle by keeping questions, annotations, and agent context in one place, which should make document review feel more interactive and less interrupt-driven.