Filesystem MCP Server

Secure File Operations for AI Agents

Official MCP reference implementation providing safe, sandboxed filesystem access with fine-grained permission controls.

Why Filesystem MCP?

🔒 Security-First Design

• Sandboxed Access: Agents can only access explicitly allowed directories
• Permission Controls: Read-only, write, or full access per directory
• Path Validation: Prevents directory traversal and unauthorized access
• Audit Trail: All operations logged for security review

🤖 Essential for Agent Workflows

• Reading documentation
• Writing code files
• Analyzing logs
• Generating reports
• Managing project files
• Organizing content

📦 Zero External Dependencies

Installation

# Official reference implementation
npm install -g @modelcontextprotocol/server-filesystem

# Or build from source
git clone https://github.com/modelcontextprotocol/servers
cd servers/src/filesystem
npm install
npm run build

Configuration

Add to your MCP client config:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/Users/yourname/Documents",
        "/Users/yourname/Projects"
      ]
    }
  }
}

Arguments = allowed directories (one or more paths)

Permission Modes

Read-Only Access:

"args": ["--read-only", "/path/to/docs"]

Full Access (default):

"args": ["/path/to/workspace"]

Example Configurations

#### Development Workspace

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/Users/dev/projects",
        "/Users/dev/workspace"
      ]
    }
  }
}

#### Documentation Access (Read-Only)

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "--read-only",
        "/Users/docs/knowledge-base"
      ]
    }
  }
}

Available Tools

Directory Operations

#### 1. List Directory (list_directory)

Agent: "What files are in my Projects folder?"
Agent: "Show contents of /workspace/src"

Returns:

• File names
• File types (file, directory, symlink)
• File sizes
• Last modified timestamps

Agent: "Create a new folder called 'components'"
Agent: "Make directory /workspace/tests"

#### 3. Move/Rename (move_file)

Agent: "Rename old-name.txt to new-name.txt"
Agent: "Move report.pdf to /Documents/Reports/"

File Operations

#### 4. Read File (read_file)

Agent: "Read the contents of config.json"
Agent: "Show me the README.md file"

Supports:

• Text files (UTF-8)
• JSON, YAML, XML
• Markdown, code files
• Large files (streaming)

Agent: "Create a file called notes.txt with meeting notes"
Agent: "Write the generated code to src/index.ts"

#### 6. Edit File (edit_file)

Agent: "Replace 'version: 1.0' with 'version: 2.0' in package.json"
Agent: "Add a new function to utils.js"

#### 7. Get File Info (get_file_info)

Agent: "When was report.pdf last modified?"
Agent: "What's the size of data.csv?"

Returns:

• File size (bytes)
• Creation time
• Last modified time
• Permissions
• File type

Advanced Operations

#### 8. Search Files (search_files)

Agent: "Find all Python files in the project"
Agent: "Search for files containing 'API_KEY'"

Search by:

• File name pattern (glob)
• File content (regex)
• File type
• Date modified

Agent: "Delete the temporary log files"
Agent: "Remove old-backup.zip"

Safety:

• Requires confirmation for large files
• Cannot delete files outside allowed directories
• Logged for audit

Agent Workflow Examples

Code Generation

Human: "Create a React component for a login form"

Agent:
1. create_directory("/workspace/components")
2. write_file("/workspace/components/LoginForm.tsx", generated_code)
3. write_file("/workspace/components/LoginForm.test.tsx", test_code)
4. "Created LoginForm component at components/LoginForm.tsx"

Log Analysis

Human: "Analyze error logs and summarize issues"

Agent:
1. list_directory("/var/log/app")
2. read_file("/var/log/app/error.log")
3. search_files(pattern="ERROR", path="/var/log/app")
4. generate_summary()
5. write_file("/reports/error-summary.md", summary)

Project Organization

Human: "Organize my documents by type"

Agent:
1. list_directory("/Documents")
2. For each file:
   - get_file_info(file)
   - Determine file type
   - create_directory("/Documents/[type]")
   - move_file(file, destination_folder)

Documentation Generation

Human: "Generate API documentation from code comments"

Agent:
1. search_files(pattern="*.ts", path="/src")
2. For each file:
   - read_file(file)
   - extract_doc_comments()
3. Generate markdown docs
4. write_file("/docs/API.md", generated_docs)

Security Model

Sandbox Enforcement

What Agents CAN Do:

• ✅ Access explicitly allowed directories
• ✅ Create/read/write files within allowed paths
• ✅ List directory contents
• ✅ Search within allowed paths

• ❌ Access parent directories (../)
• ❌ Access system files (/etc/, /sys/)
• ❌ Follow symlinks outside allowed paths
• ❌ Execute binaries or scripts
• ❌ Modify file permissions

Path Validation

Allowed: /Users/dev/projects
Agent tries: /Users/dev/projects/src/index.ts → ✅ Allowed
Agent tries: /Users/dev/projects/../secret → ❌ Blocked
Agent tries: /etc/passwd → ❌ Blocked

Best Practices

• Principle of Least Privilege
• Grant only necessary directories
• Use --read-only when write not needed
• Never Allow Root Access
• Don't add / or system directories
• Restrict to user workspace
• Audit Agent Actions
• Review MCP server logs regularly
• Monitor for unexpected file access patterns
• Separate Sensitive Data
• Keep credentials, keys in separate directories
• Don't include in allowed paths

Use Cases

📝 Content Management

🤖 Code Assistants

📊 Data Analysis

🗂️ File Organization

📚 Knowledge Base

🔍 Log Analysis

Performance

Large Files

• Streaming for files >10MB
• Incremental reads supported
• Memory-efficient processing

Directory Scanning

• Recursive search optimized
• Glob pattern matching
• Ignore patterns (e.g., node_modules/)

Concurrent Operations

• Safe for parallel file access
• Atomic write operations
• File locking where needed

Troubleshooting

"Permission denied" Error

• Verify path is in allowed directories
• Check filesystem permissions
• Ensure MCP server has read/write access

"Path not found" Error

• Confirm directory exists
• Check for typos in path
• Verify path format (absolute vs relative)

Read-Only Mode Issues

• Can't write in --read-only mode
• Reconfigure server with write access if needed

vs Other File Access Methods

Resources

• GitHub: https://github.com/modelcontextprotocol/servers/tree/main/src/filesystem
• MCP Docs: https://modelcontextprotocol.io/
• Security Best Practices: https://modelcontextprotocol.io/docs/concepts/security

Advanced Configuration

{
  "mcpServers": {
    "filesystem": {
      "command": "node",
      "args": [
        "/path/to/filesystem-server/build/index.js",
        "/workspace",
        "/documents"
      ],
      "env": {
        "MAX_FILE_SIZE": "10485760",
        "ENABLE_LOGGING": "true",
        "LOG_PATH": "/var/log/mcp-filesystem.log"
      }
    }
  }
}

Safe, secure filesystem access for agents: From code generation to log analysis, Filesystem MCP is the foundation for agent file operations.