Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by fabienvauchelles • Tools & CLI
A Node.js MCP server that exposes a sandboxed set of filesystem operations (read, write, search, move, delete, diff, checksums, and metadata) for use by agents and tools.
Read, patch, and diff multiple source files across a project while preserving safe sandboxing to allowed directories.
Search codebases or document collections by filename, glob patterns, or content regex and return matching lines with context.
Create, move, delete, and verify files in bulk (including checksum generation/verification and directory tree inspection) as part of automation workflows.
This server implements the Model Context Protocol (MCP) to provide programmatic, multi-file filesystem operations within explicitly allowed directories. It supports reading, creating, appending, patching, moving, copying, deleting, searching (name, glob, content regex), diffing, counting lines, and generating/verifying checksums, plus directory-tree and file-metadata APIs. Operations are sandboxed to directories passed as arguments (e.g., mounted under /projects in Docker), helping contain access and improve security. The design favors batch operations with partial-failure reporting, making it useful for agents that need reliable file-system automation across multiple files or projects.
Read the complete contents of a file as text. DEPRECATED: Use read_text_file instead.
Read the complete contents of a file from the file system as text. 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. Use the 'head' parameter to read only the first N lines of a file, or the 'tail' parameter to read only the last N lines of a file. Operates on the file as text regardless of extension. Only works within allowed directories.
Read an image or audio file. Returns the base64 encoded data and MIME type. 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.
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.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.