MCP Server
未认领MCP server for Jungle Grid lets agents submit, monitor, and retrieve logs from AI workloads.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'jungle-grid-mcp-server' -- 'npx' '-y' '@jungle-grid/mcp'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
11 个工具中显示 11 个
文档中列出的工具 (11)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
cancel_job
Request cancellation of a non-terminal job.
estimate_job
Estimate routing, capacity source, and expected cost without creating work.
get_artifact
Create temporary artifact download information.
get_job
Read job status, phase, scheduling, billing, and artifact readiness.
get_job_events
Read lifecycle events for scheduling, provisioning, startup, failures, and cancellation.
get_job_logs
Read persisted runtime and workload logs.
list_artifacts
List managed output artifacts for a job.
list_job_inputs
List uploaded inputs and scripts for the authenticated account.
list_jobs
List recent jobs.
submit_job
Submit a workload. This may start compute and incur usage charges.
upload_job_input
Create a signed upload slot for an input file or script.