$ loading_
Manage Agent Platform sandboxes with MCP start, stop, and status tools.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "agent-platform-api" yet — see the docs or source repo.
Use agent-platform-api to start a new sandbox environment and return the result.
Returns sandbox start success info, environment ID, or an error reason.
Check the current sandbox status and tell me whether it is running.
Returns the current status, such as running, stopped, or unavailable.
Stop the specified sandbox and confirm that it is shut down.
Returns the stop operation result and final status.
DevOps engineers or developers can use it to start, inspect, and stop sandboxes on demand. It reduces manual work in workflows that frequently create and tear down test environments.
When a workflow depends on a sandbox, you can check its status before proceeding. This avoids wasting time on an unavailable environment.
It is an MCP server for the Agent Platform API, used to manage sandbox environments through the MCP protocol. It provides lifecycle tools such as start, stop, and status checks.
Based on the description, it mainly supports sandbox lifecycle operations, including start, stop, and status checks. See the source repository for more details.
The provided information only says it accesses the Agent Platform API via MCP and does not include setup or credential requirements. See the source repository for specific prerequisites.
A sandbox server for testing and debugging MCP tools and interactions.
Give AI agents authenticated sandbox access and a restricted path for safe production deploys.
Run code and Postman collections in isolated sandboxes with real-time management.
Run commands, manage long jobs, and transfer files in AI sandboxes.
Verify MCP server responses by returning a unique canary identity string.
Run SQL, APIs, and sandboxed Python for multi-step research and data tasks.