loommux
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOOMMUX_MONITOR_URL | No | Override the monitor event-ingest URL. | |
| LOOMMUX_MONITOR_DISABLED | No | Set to 1 to disable monitor publishing. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_cellA | 向持久 IPython kernel 提交一个 IPython cell。 请你使用 IPython 的思想来优雅使用本系列工具。 输入一格 IPython cell,变量、导入和其他 namespace 状态与当前持久 IPython 会话中的后续 cell 共享。 loommux cell magiccell 第一行写 等待有两个计时器,对应 HTTP 客户端的总超时与 read timeout(CI 里是 job timeout 与 no_output_timeout):
cell 跑完立即返回;计时器先到时,结果写明 running 与原因,附最后几行输出。
到点只交还控制权,cell 照常运行:接着用 不写时两个都是 10 秒,几秒内结束的 cell 不用写。要跑更久,就按这次具体在跑的东西估两个整数秒,
不写 30、120、600 这类凑整的数: 每个结果第一行写着这次执行跑了多久,如
什么时候用呢?
主 kernel第一个 cell 用
图像展示使用 IPython 执行编号与后续操作提交成功可以获得一个 |
| statusA | 返回 workspace、kernel 与最近执行记录的观察状态。 状态范围还返回当前 IPython 工作台启动时解析的 workspace、其
IPython 通过原生 ZMQ 协议连接,拥有完整能力。 Returns: 当前 IPython 工作台与 kernel 的状态快照。 |
| execution_statusA | 返回一个 execution 的状态与元数据。 选择规则提供 |
| read_outputA | 读取一个 execution 的指定输出流。 选择与流
行坐标
负数按行号从尾部数,两端照样都含: |
| search_outputA | 在一个 execution 的指定输出流中搜索文本或正则表达式。 选择与匹配
命中上下文每条命中保留原始所选流行号,并以 |
| waitA | 等待一个 execution 结束,或两个计时器之一到点。 两个计时器与 cell 头的 到点只结束这次调用,cell 照常运行,结果写明 running 与原因,附最后几行输出;
之后可以再调用本工具,或用 选择
完整输出交付当所选 execution 的 cell 头含 |
| interruptA | 向当前正在运行的 execution 发送 kernel 中断信号。 中断语义kernel 到达 IOPub Returns:
已发送信号时返回目标 |
| restartA | 重启 IPython kernel。 重置边界若存在 running execution,它会先被终止;随后旧 kernel 停止并创建替代 kernel。 Returns: 新 kernel 的状态与 PID;重启失败时返回 workspace 或 kernel 启动错误。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Most tools are clearly distinct (run_cell, wait, interrupt, restart, read_output, search_output), but execution_status and status overlap heavily — both report status about the kernel/executions, with fuzzy boundaries that force the agent to reason about which one answers its question. The verbose descriptions help clarify but don't fully resolve this confusion.
All tools use snake_case and a readable action-oriented convention (run_cell, read_output, search_output, interrupt, restart, wait). The main deviation is the pair 'status' vs 'execution_status', where one is a bare noun and the other a noun_noun compound, creating slight inconsistency.
Eight tools is well-scoped for a persistent IPython kernel session manager, covering execution, waiting, output inspection, search, interrupt, restart, and status without bloat. Each tool earns its place in the workflow.
The execution lifecycle is well covered (submit, wait, read, search, interrupt, status, restart). However, kernel lifecycle operations mentioned in the docs — create/attach, rename, list kernels, and recycle/kill — are exposed only via the Python loommux object, not as tools, leaving gaps an agent must work around through run_cell code.