Board Terminal Skill
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Board Terminal Skillrun 'cat /proc/cpuinfo' on the dev board"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Board Terminal Skill
MCP server exposing one tool, board_terminal, for running shell commands on a Linux development board through a controlled executor.
The first backend is UART serial. SSH is represented by a placeholder interface so it can be added without changing the MCP tool contract.
Tool
Input:
{
"command": "cat /proc/cpuinfo"
}Output:
{
"success": true,
"stdout": "processor : 0\n...",
"stderr": "",
"exit_code": 0,
"elapsed_ms": 135
}For serial shells there is no reliable process exit status unless the command wrapper reports it. This implementation wraps every command and captures a marker containing $?, so exit_code is the command exit code when the shell supports standard POSIX syntax. If the marker cannot be parsed but the prompt returns, exit_code defaults to 0.
Related MCP server: serial-mcp
Configuration
Environment variables:
Variable | Default | Description |
|
| Backend name. Currently only |
|
| Serial device path, for example |
|
| UART baud rate. |
|
| Per-read timeout in seconds. |
|
| Command completion timeout in seconds. |
|
| Stable shell prompt used to detect completion. |
|
| Serial text encoding. |
Run
Install dependencies:
python3 -m pip install -e .Start the MCP server over stdio:
board-terminal-skillExample MCP client configuration:
{
"mcpServers": {
"board-terminal": {
"command": "board-terminal-skill",
"env": {
"BOARD_SERIAL_PORT": "/dev/ttyUSB0",
"BOARD_SERIAL_BAUDRATE": "115200"
}
}
}
}Available Tools
1 toolboard_terminalC
Run a shell command on the connected Linux development board.
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It only states 'Run a shell command,' omitting critical details such as destructive potential, output format, timeout behavior, or authentication needs for a terminal command runner.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no unnecessary words. It is appropriately concise for a simple tool with one parameter.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite low complexity (1 parameter, no nested objects), the description does not cover return values or side effects, even though an output schema exists. The absence of behavioral context makes it incomplete for an agent to use safely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description adds no meaning beyond what the parameter name 'command' implies. No format, constraints, or examples are given, failing to compensate for the schema's lack of description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'run' and the resource 'shell command on connected Linux development board'. It is specific enough to convey the tool's function. With no sibling tools, differentiation is not needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when or when not to use the tool is provided. There is no mention of prerequisites, safety concerns, or alternatives, leaving the agent without context for appropriate invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
board_terminal
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap, so disambiguation is perfect.
The single tool name 'board_terminal' is clear and follows a consistent style, making it predictable.
One tool is minimal but appropriate for a focused 'Board Terminal Skill' that only needs to run shell commands. However, it is on the thin side.
The tool fully covers the stated purpose of running shell commands on a board, with no obvious missing operations for that narrow scope.
Maintenance
Related MCP Connectors
MCP server for Klever blockchain smart contract development.
MCP server to assist with JxBrowser development.
Related MCP Servers
- AlicenseAqualityAmaintenanceMCP server that lets LLMs talk to serial devices: microcontrollers, routers, modems, embedded Linux, anything with a UART.235MIT
- FlicenseAqualityDmaintenanceMCP server for serial port communication. Provides tools to open, read, write, and manage serial ports through the Model Context Protocol.10-
- FlicenseBqualityDmaintenanceMCP server for controlling MicroPython devices (ESP32, RP2040, etc.) via USB Serial or WebREPL, enabling code execution, file operations, and device management from MCP clients.299-
- FlicenseAqualityBmaintenanceHeadless local stdio MCP server for board-debug operations, allowing compatible clients to use tools for firmware debugging and board management.201-