Loading ToolBench
An MCP server that adds local terminal automation capabilities to AI agents.
This server has critical gaps across naming, descriptions, schemas, and error handling. Tool names lack action verbs (bash, python_code, python_file are vague). Descriptions are present but generic and under 100 chars, failing to explain WHEN to use each tool or that they execute irreversible code. Input schemas exist but lack parameter descriptions entirely, the 'command' and 'code' parameters have no guidance on format, constraints, or examples. No output schemas documented. Error handling is minimal: subprocess errors return raw stderr without recovery guidance. The server exposes dangerous operations (bash execution, arbitrary Python code) with no permission gates, confirmation steps, or audit trails. No tool annotations (destructiveHint, readOnlyHint) despite clear risk levels.
This function will execute a bash command and return the output. This function is useful for executing bash commands including creating files, directories, and other bash commands.
This function will create a folder with the given name. If the folder already exists, it will return a message indicating that the folder already exists.
This function will delete a folder with the given name. If the folder does not exist, it will return a message indicating that the folder does not exist.
This function will return a list of files that match the given pattern. This function is useful for finding files in a directory.
This function will search for the given pattern in the specified file and return the matching lines.
This function will execute a python code and return the output.
Dangerous operations (bash, python_code, python_file) lack permission gates, confirmation steps, or dry-run support. Agents can execute arbitrary code without safeguards.
Input parameters have no descriptions. 'command', 'code', 'file', 'pattern', 'folder', 'content' lack guidance on format, constraints, or valid ranges. LLMs cannot infer parameter meaning.
Tool names lack action verbs. 'bash', 'python_code', 'python_file' are vague. Should be 'execute_bash_command', 'execute_python_code', 'execute_python_file' to signal intent clearly.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 34 | 2026-07-28+ | v2 |
This function will execute a python file and return the output.
This function will read the contents of a file and return it as a string.
This function will write the given content to a file. If the file does not exist, it will be created.
No output schemas documented. Tools return raw strings or lists without structure. LLMs cannot plan downstream calls or extract typed fields reliably.
Error handling returns raw exception strings without recovery guidance. 'CalledProcessError' or generic 'Exception' messages tell LLMs nothing about what to do next.