mcpignore-filesystem MCP Server

What does “mcpignore-filesystem” MCP Server do?

The mcpignore-filesystem MCP Server is a Node.js-based tool that enhances AI assistant development workflows by providing secure, granular control over filesystem access. Building on top of the standard Filesystem MCP Server, this server introduces .mcpignore file support, enabling you to restrict which files and directories your MCP clients (such as AI agents) can interact with. By specifying ignore patterns similar to .gitignore, you can protect sensitive data and ensure that only authorized files are accessible for operations like reading, writing, directory management, and searching. This server empowers development tasks involving file management while maintaining strict data security and access controls, making it ideal for teams needing robust, customizable filesystem interfaces for AI-driven workflows.

List of Prompts

No prompt templates are mentioned in the repository.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No explicit MCP resources are documented in the repository.

List of Tools

• read_file: Reads a file unless it matches a .mcpignore pattern (Blocked for ignored paths).
• read_multiple_files: Reads multiple files unless ignored (Blocked for ignored paths).
• write_file: Writes to a file unless ignored (Blocked for ignored paths).
• edit_file: Edits a file unless ignored (Blocked for ignored paths).
• create_directory: Creates a directory unless ignored (Blocked for ignored paths).
• list_directory: Lists directory contents unless ignored (Blocked for ignored paths).
• move_file: Moves files or directories unless ignored (Blocked for ignored paths).
• get_file_info: Retrieves file metadata unless ignored (Blocked for ignored paths).
• directory_tree: Retrieves the structure of directories (Allowed, only shows names).
• search_files: Searches for files (Allowed, only shows names).
• list_allowed_directories: Lists directories allowed for access (N/A for ignore logic).

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Granular Filesystem Security: Developers can offer AI agents controlled access to project directories, protecting sensitive files (e.g., .env, secrets, credentials) by specifying them in .mcpignore.
• Safe Codebase Exploration: AI tools can analyze and navigate large codebases while ensuring confidential or proprietary files are excluded from exposure.
• Automated File Management: Automate routine tasks like organizing, searching, or moving files across directories, with robust access restrictions via .mcpignore.
• Collaborative Development Environments: Safely expose shared directories to AI-driven assistants for editing or searching while blocking access to internal or temporary files.
• Compliance and Audit: Enforce data compliance by ensuring specific data types or files are inaccessible to automated tools, aiding in audit and governance.

How to set it up

Windsurf

No specific Windsurf instructions provided in the repository.

Claude

1. Ensure Node.js and npx are installed.
2. Open your claude_desktop_config.json.
3. Add the MCP server configuration as shown below.
4. Save the file and restart Claude.
5. Verify the server is running and accessible.

{
  "mcpServers": {
    "mcpignore-filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@cyberhaven/mcpignore-filesystem",
        "/Users/<username>/Desktop",
        "/path/to/other/allowed/dir"
      ]
    }
  }
}

Securing API Keys (example):

{
  "mcpServers": {
    "mcpignore-filesystem": {
      "command": "npx",
      "args": [ ... ],
      "env": {
        "API_KEY": "${MCP_SERVER_API_KEY}"
      },
      "inputs": {
        "api_key": "${MCP_SERVER_API_KEY}"
      }
    }
  }
}

Cursor

1. Ensure Node.js and npx are installed.
2. Open your mcp.json configuration file.
3. Add the server configuration as below.
4. Save the file and restart Cursor.
5. Confirm server connectivity.

{
  "mcpServers": {
    "mcpignore-filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@cyberhaven/mcpignore-filesystem",
        "/Users/<username>/Desktop",
        "/path/to/other/allowed/dir"
      ]
    }
  }
}

Securing API Keys: (see Claude example above)

Cline

1. Ensure Node.js and npx are installed.
2. Open your cline_mcp_settings.json.
3. Insert the server configuration.
4. Save and restart Cline.
5. Check server availability.

{
  "mcpServers": {
    "mcpignore-filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@cyberhaven/mcpignore-filesystem",
        "/Users/<username>/Desktop",
        "/path/to/other/allowed/dir"
      ]
    }
  }
}

Securing API Keys: (see Claude example above)

Windsurf

No setup instructions provided.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mcpignore-filesystem": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “mcpignore-filesystem” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available information, this MCP server offers robust and clearly documented filesystem tooling with strong security features, but lacks prompt and resource templates. There is also no explicit mention of Roots or Sampling support. As such, it is a strong choice for secure file management, but may be less suitable for workflows requiring prompt templates or advanced resource handling.

MCP Score

Rating:
I would rate this MCP server a 6/10. It has a clear security focus, documented tooling, and licensing, but lacks prompt templates, resource definitions, and evidence of roots or sampling support. Its value is strongest for teams seeking secure, ignore-based filesystem access for AI agents.