save-filesystem-mcp
mcp server to modify files savely in a root directory where user should not be able to escapce from
Documentation
Filesystem MCP
> [!WARNING]
> Should not be able to modify files in other folders then specified root folder but this needs to be seen ...
Simple filesystem MCP that allows to create, read, update and delete files in a specified root folder. The root folder is specified as an argument to the node call.
The agent should not be able to modify files in other folders outside the root folder (not guaranteed though).
How to install:
> [!TIP]
> You need > Node.js 12 to run this MCP. You might need to use it over nvm or similar.
Modify e.g. your Clause MCP config e.g. under MAC via (see also claude documentation):
~/Library/Application\ Support/Claude/claude_desktop_config.jsonand add the server:
{
"mcpServers": {
"save-filesystem-mcp": {
"command": "node",
"args": [
"PATH_TO_FOLDER/save-filesystem-mcp/build/index.js",
"ABSOLUTE_FOLDER_FOR_CLAUDE_TO_WORK_WITH"
]
}
}
}Then start claude and ask it to code a game for you. It will use the MCP to create, read, update and delete files in the specified root folder.
Frequently asked questions
What is save-filesystem-mcp?
save-filesystem-mcp is mcp server to modify files savely in a root directory where user should not be able to escapce from
How do I install save-filesystem-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is save-filesystem-mcp open source?
Yes — it is hosted on GitHub at https://github.com/sebastianbachmaier/save-filesystem-mcp.
Related MCP tools
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Built for the Model Context Protocol to enhance AI capabilities.
Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini...
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, ...
Composio equips your AI agents & LLMs with 100+ high-quality integrations via function calling for the Model Context Protocol. Enhance AI assistants with powerf
Playwright MCP server TypeScript-based implementation. Trusted by 22000+ developers. Trusted by 22000+ developers. Trusted by 22000+ developers.
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Lan...
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP