darkside-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Enable debug logging | false |
| PYTHON_PATH | No | Python executable path | python |
| ALLOWED_PATHS | No | Specific paths to allow (more restrictive than drives) | |
| ALLOWED_DRIVES | No | Comma-separated drive letters your AI can access | C,F |
| PYTHON_TIMEOUT | No | Default Python timeout (ms) | 30000 |
| POWERSHELL_PATH | No | PowerShell executable | powershell.exe |
| POWERSHELL_TIMEOUT | No | Default PowerShell timeout (ms) | 60000 |
| PYTHON_MAX_TIMEOUT | No | Max Python timeout (ms) | 300000 |
| POWERSHELL_MAX_TIMEOUT | No | Max PowerShell timeout (10 min) | 600000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_directoryA | List contents of a directory. Returns file/folder names, sizes, and timestamps. |
| read_fileA | Read contents of a file. Supports text files with configurable encoding. |
| write_fileA | Write or update a file. Automatically creates backup of existing files. |
| search_filesA | Search for files using glob patterns. Supports wildcards like *.json, **/*.py |
| get_file_infoA | Get file or directory metadata including size, timestamps, and type. |
| create_directoryB | Create a new directory. Creates parent directories as needed. |
| delete_fileA | Delete a file. Creates backup before deletion by default. |
| run_python_scriptA | Execute a Python script file with arguments. MCP-safe subprocess handling with captured stdout/stderr. |
| run_python_codeB | Execute inline Python code. Creates temp file, runs it, cleans up. Includes basic security checks. |
| check_python_syntaxA | Check Python code syntax without executing. Uses Python's ast.parse. |
| get_python_infoA | Get Python interpreter information including version, path, and platform. |
| run_powershellB | Execute a PowerShell command with full system access. No restrictions - for trusted AI partners. Can access registry, services, network, processes, and more. |
| run_powershell_scriptA | Execute a PowerShell script file (.ps1) with arguments. Full system access with MCP-safe subprocess handling. |
| get_powershell_infoA | Get PowerShell and system information including version, OS, machine name, and user. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Most tools target distinct file, Python, or PowerShell operations with clear resource/action boundaries. The only real ambiguity is between run_python_script/run_python_code and run_powershell/run_powershell_script, but the script-vs-inline distinction is described.
All tools use lowercase snake_case with a clear verb-first pattern such as list_, read_, write_, run_, and get_. The naming is highly predictable and consistent across file, Python, and PowerShell clusters.
14 tools is at the upper edge of a reasonable scope and every major cluster has a purpose. The environment-info tools are somewhat peripheral, but the overall count is not bloated.
The file operations cover create/read/update/delete/list/search/info, and both Python and PowerShell support script execution plus diagnostics. Missing file copy/move/rename or directory deletion are minor gaps that agents can usually work around.