Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 21 Oct 2026
One change · api

self-hosted-sandboxes-custom-tools changedmanaged-agents/self-hosted-sandboxes-custom-tools

Nearest release: v2.1.307, published an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+4added
Lines−4removed
From line 10 where the diff opens
First seen 2 Oct 2026 this site's first read of the page
Recorded edits8to this page, all time

The whole hunk

from line 10, old and new numbered
/
lines
from line 10
1010 betaHeader: managed-agents-2026-04-01
1111---
1212 
13[Custom tools](https://platform.claude.com/docs/en/managed-agents/tools#custom-tools) are tools your own code executes: the agent emits an `agent.custom_tool_use` event and waits for a matching `user.custom_tool_result`. Your worker can be that code. Because it runs inside your sandbox, the tool reaches the internal services, credentials, and network egress you configured for the sandbox, and nothing more.
13[Custom tools](https://platform.claude.com/docs/en/managed-agents/tools#custom-tools) are tools your own code runs: the agent emits an `agent.custom_tool_use` event and waits for a matching `user.custom_tool_result`. Your worker can be that code. Because it runs inside your sandbox, the tool reaches the internal services, credentials, and network egress you configured for the sandbox, and nothing more.
1414 
1515The environment key authorizes posting custom tool results, so your Claude API key stays off the worker host.
1616 
from line 781
781781Two cases need extra work:
782782 
783783* **Two servers expose the same tool name:** Define the wrapper yourself under a prefixed name and have it call the server's original tool name.
784* **A generator such as pydantic factors schemas into `$defs`:** Inline those schemas before you declare the tool.
784* **A generator such as Pydantic factors schemas into `$defs`:** Inline those schemas before you declare the tool.
785785 
786786### Tool failures surface as error tool results
787787 
788788When the MCP server reports a tool error, the worker posts an error tool result the model can react to. MCP content with no tool result equivalent, such as audio blocks and resource links, also surfaces as an error.
789789 
790Set a timeout on the MCP client for a faster and clearer failure, as the Python worker example does with `read_timeout_seconds`. See [A wrapped MCP tool call hangs](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-operations#a-wrapped-mcp-tool-call-hangs) for what happens without one.
790Set a timeout on the MCP client for a faster and clearer failure, as the Python worker example does with `read_timeout_seconds`. See [A wrapped MCP tool call hangs](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-operations#a-wrapped-mcp-tool-call-hangs) for what occurs without one.
791791 
792792### Wrap only servers you operate or trust
793793 
from line 795
795795 
796796### Permission policies do not apply
797797 
798[Permission policies](https://platform.claude.com/docs/en/managed-agents/permission-policies#custom-tools) govern the built-in and MCP toolsets. The worker executes every wrapped tool call the model makes, so put any approval step in your own tool code.
798[Permission policies](https://platform.claude.com/docs/en/managed-agents/permission-policies#custom-tools) govern the built-in and MCP toolsets. The worker runs every wrapped tool call the model makes, so put any approval step in your own tool code.
799799 
Feedback