HDFS MCP Server

Access and manage files on HDFS clusters using the MCP protocol, supporting operations like upload, download, move, and copy.

HDFS MCP Server is a controller based on MCP (Model Context Protocol) that provides access to HDFS clusters through the MCP protocol. The server supports basic HDFS operations such as file upload, download, move, copy, and provides friendly error handling and connection testing capabilities.

- Python 3.11 or higher
- Hadoop client installed and configured
- uvpackage manager

git clone https://github.com/will-sh/hdfs-mcp.git cd hdfs-mcp

# Example using pyenv pyenv install 3.11

uv venv source .venv/bin/activate # macOS/Linux # .\.venv\Scripts\activate # Windows

{ "mcpServers": { "hdfs-controller": { "command": "uv", "args": [ "--directory", "/path/to/your/hdfsmcp", "run", "hdfs.py" ], "env": { "HDFS_NAMENODE": "your_namenode_hostname", "NAMENODE_PORT": "your_namenode_port" } } } }

Replace the following with your actual configuration:

- /path/to/your/hdfs-mcp: Replace with your project's actual path
- your_namenode_hostname: Replace with your HDFS NameNode hostname
- your_namenode_port: Replace with your HDFS NameNode port (if not specify the default port is 8020)

The HDFS MCP provides the following HDFS operations:

- List directory contents
- Read file contents
- Create directories
- Delete files/directories
- Upload files to HDFS
- Download files from HDFS
- Get file/directory information
- Get disk usage
- Get cluster status
- Copy/move files within HDFS
- Ensure Hadoop client is properly installed and configured
- EnsureHADOOP_HOMEenvironment variable is set
- Ensurehdfscommand is in your system PATH

If you encounter connection issues, check:
- HDFS NameNode accessibility
- Port configuration
- Network connectivity
- Hadoop client configuration
- Kerberos ticket is valid

- Ensure you have sufficient permissions to access the HDFS cluster
- Large file operations may take longer, please be patient
- It's recommended to test the connection before operations

Parses various file formats using the 302.AI API, requiring a 302AI_API_KEY.

A local server that allows AI to execute Windows CMD commands, read/write files, and manage directories within a specified path.

Filesystem agent memory working with consolidation Daemon on your machine

An AI-powered MCP server for advanced file system operations, including search, comparison, and security analysis.

Securely browse and read files within an Android project, with built-in validation and access controls for sensitive directories.

Build a persistent, local knowledge base in Markdown files through conversations with LLMs.

A read-only MCP server for querying live FTP data using the CData JDBC Driver.

An MCP server for viewing, editing, and creating text files, based on the Claude built-in text editor tool.

Convert PDF, Word, Excel, PowerPoint, EPUB, HEIC and images from Claude or Cursor, with 35 converters exposed through just two MCP tools.

A cross-platform filesystem server for Linux, macOS, and Windows with secure path restrictions.