Skip to main content
Glama
mako10k
by mako10k

terminal_operate

Unify host-terminal operations by creating sessions, sending input, and retrieving output with automatic position tracking across multiple shell types.

Instructions

Unified host-terminal operations: create sessions, send input, and get output with automatic position tracking. Creation and input are unavailable in restrictive sandbox mode.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inputNoInput to send to terminal. Can be partial input or complete command.
commandNoCommand to execute in a terminal. Terminal creation and input are unavailable in restrictive mode.
executeNoWhether to press Enter after sending input (execute command)
send_toNoProgram guard target to ensure input is sent to the correct process. Can be process name, path, "pid:12345", "sessionleader:", or "*" for any process.
dimensionsNoTerminal dimensions. For new terminals: initial size. For existing terminals: resize if different from current size.
get_outputNoWhether to retrieve terminal output after operations
shell_typeNoShell type for new terminalbash
force_inputNoForce input even if unread output exists. Default: false (input rejected if unread output exists).
terminal_idNoExisting terminal ID to use. If not provided, creates a new host terminal when command is specified. Creation is unavailable in restrictive mode.
include_ansiNoInclude ANSI codes in output
output_linesNoNumber of output lines to retrieve
session_nameNoName for new terminal session
control_codesNoWhether to interpret input as control codes
response_levelNoResponse detail level: minimal (only essential data, fastest), standard (balanced info for most use cases), full (complete details, maximum information)standard
output_delay_msNoDelay in milliseconds before retrieving output (allows command to complete)
working_directoryNoWorking directory for new terminal
return_terminal_infoNoInclude terminal information in response
environment_variablesNoEnvironment variables for new terminal

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv2.8.1

TDQS

B3.1/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

没有注解,描述承担全部行为披露责任。它提及了自动位置跟踪和限制模式下的不可用性,提供了部分行为约束;但未说明权限要求、影响范围、失败行为或返回内容,对18个参数的综合操作工具来说信息仍偏少。

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

描述简短且有信息密度,将核心功能列在句首,随后补充关键限制。没有冗余,但内容非常少,对一个多功能工具来说略过于简略,故不能给出满分的5分。

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

考虑到工具包含18个参数、嵌套对象且无输出 schema,描述只提供一个高度概括的定义,没有解释参数之间的协作,比如何时可新建会话、何时复用 terminal_id。对智能体正确调用来说,上下文仍不充分。

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

输入 schema 的字段描述覆盖率达100%,所有参数在 schema 中均有说明。描述并未额外提供参数关联性或使用层面的语义,例如 terminal_id 与 command 条件的关系,符合高覆盖下的 baseline 3分。

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

描述以一个明确的动名词序列(create sessions, send input, get output)配上资源(host terminals)开头,能够让智能体立即理解工具职责。但它没有与兄弟工具(如 shell_execute、terminal_get_info)做区分,也没有指出自己与这些工具的分界,因此不是最高的5分。

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

描述完全没有说明何时使用本工具而非兄弟工具(如 shell_execute 用于直接执行命令),也没有给出任何流程性的使用指引。唯一提及的‘在限制模式下不可用’是环境限制而非选择条件。

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mako10k/mcp-shell-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server