$ loading_
Securely read, write, and list files inside AI-driven workflows.
This tool is described as an open-source lightweight MCP server for basic file operations, with no required secrets and no declared remote endpoints. Its main exposure is local code execution and file read/write access, which are typical for this class of tool; overall it appears low-to-moderate risk with some caution due to limited source maturity signals.
The materials explicitly state that no keys or environment variables are required, and there is no indication of credential collection, storage, or transmission, so credential abuse exposure appears low.
No remote endpoints or external service connections are declared. Based on the materials, the functionality is focused on local file operations, with no factual indication of sending user data to third parties.
The system checks indicate that the tool can execute code/spawn processes. As an MCP tool, this means it runs locally and invokes system-level file-related capabilities; this is typical for the category, but it should still be run in a constrained environment.
The description explicitly states support for reading, writing, and listing files, indicating access to local file data. The materials do not specify directory scope, sandbox boundaries, or least-privilege controls, so the potentially broad file access surface warrants caution.
A public source repository is available for review, which is a positive factor that lowers risk. However, it comes from a third-party registry, the license is undeclared, community adoption is 0 stars, and maintenance status is unknown, indicating weak maturity and upkeep signals.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "files-mcp-ts" yet — see the docs or source repo.
Use files-mcp-ts to read config.json in the project root and summarize the key settings.
A summary of the config file with major fields and their purposes.
Use files-mcp-ts to write the following weekly report into reports/weekly-summary.md, and create the directory first if it does not exist.
The specified Markdown file is created and saved, with confirmation of successful write.
Use files-mcp-ts to list all files in the data directory and group them by file type.
A directory file listing grouped and presented by file type.
Enable LLMs to perform efficient intelligent file operations with minimal token usage.
Safely read, write, search, and manage files in a sandboxed environment.
Access, list, read, and search files in configured folders via MCP.
Safely read, write, and manage files in a local AgentFiles directory.
Enhanced filesystem MCP tool for searching, reading, editing, deleting, and running commands.
Let AI read, write, search files, and run local commands.