A Model Context Protocol server for safety training of language models, focusing on learning to refuse falsely benign MCP exploits using improved preference alignment techniques including DPO, SafeDPO, and RAG-Pref.
This file-system MCP server has well-structured tool definitions with consistent naming (verb_noun pattern), comprehensive descriptions (avg 180 chars, within 10-1024 baseline), and clear parameter documentation. All 11 tools follow a coherent interface pattern. However, output schemas are not explicitly documented in the source code, only input schemas are visible. Error handling descriptions are generic ('provides detailed error messages') without actionable recovery guidance. No tool annotations (readOnlyHint/destructiveHint) are present despite clear risk classifications. Parameter descriptions lack format constraints (e.g., path validation rules, encoding details for read_file). The server demonstrates solid fundamentals but lacks production-grade error recovery and output schema documentation.
Create a new directory or ensure a directory exists. Can create multiple nested directories in one operation. If the directory already exists, this operation will succeed silently. Perfect for setting up directory structures for projects or ensuring required paths exist. Only works within allowed directories.
Get a recursive tree view of files and directories as a JSON structure. Each entry includes 'name', 'type' (file/directory), and 'children' for directories. Files have no children array, while directories always have a children array (which may be empty). The output is formatted with 2-space indentation for readability. Only works within allowed directories.
Make line-based edits to a text file. Each edit replaces exact line sequences with new content. Returns a git-style diff showing the changes made. Only works within allowed directories.
Retrieve detailed metadata about a file or directory. Returns comprehensive information including size, creation time, last modified time, permissions, and type. This tool is perfect for understanding file characteristics without reading the actual content. Only works within allowed directories.
Returns the list of directories that this server is allowed to access. Use this to understand which directories are available before trying to access files.
Output schemas not documented. Tool descriptions state what is returned (e.g., 'git-style diff', 'JSON structure', 'comprehensive information') but formal output schema definitions are absent from source code. LLMs cannot plan downstream tool calls or extract specific fields without knowing return structure.
No tool annotations (readOnlyHint/destructiveHint/idempotentHint). Tools are classified with Risk labels (READ_ONLY, WRITE) in metadata but MCP tool annotations are not present. This prevents clients from rendering safety warnings or enforcing permission gates.
Error handling lacks actionable recovery guidance. Descriptions say 'provides detailed error messages' but do not specify what the LLM should do on failure (retry, ask user, call alternative tool). Pattern requires: 'User not found. Try search_users() with a partial name.'
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
Get a detailed listing of all files and directories in a specified path. Results clearly distinguish between files and directories with [FILE] and [DIR] prefixes. This tool is essential for understanding directory structure and finding specific files within a directory. Only works within allowed directories.
Move or rename files and directories. Can move files between directories and rename them in a single operation. If the destination exists, the operation will fail. Works across different directories and can be used for simple renaming within the same directory. Both source and destination must be within allowed directories.
Read the complete contents of a file from the file system. Handles various text encodings and provides detailed error messages if the file cannot be read. Use this tool when you need to examine the contents of a single file. Only works within allowed directories.
Read the contents of multiple files simultaneously. This is more efficient than reading files one by one when you need to analyze or compare multiple files. Each file's content is returned with its path as a reference. Failed reads for individual files won't stop the entire operation. Only works within allowed directories.
Recursively search for files and directories matching a pattern. Searches through all subdirectories from the starting path. The search is case-insensitive and matches partial names. Returns full paths to all matching items. Great for finding files when you don't know their exact location. Only searches within allowed directories.
Create a new file or completely overwrite an existing file with new content. Use with caution as it will overwrite existing files without warning. Handles text content with proper encoding. Only works within allowed directories.
Parameter descriptions lack format constraints. 'path' parameters do not specify validation rules (allowed characters, max length, symlink handling). 'pattern' in search_files lacks regex syntax or case-sensitivity details. Constraints should be explicit, not inferred.
No pagination or result limits documented. list_directory and directory_tree do not specify max results or pagination strategy. Large directories could return thousands of entries, exhausting context window. Baseline pattern requires limit + offset/cursor.