ScriptFlow MCP Server
ScriptFlow is a script workflow management system that transforms complex, repetitive AI interactions into persistent, executable scripts that can be managed, version controlled, and reused across sessions.
Get this MCP server
ScriptFlow is a script workflow management system that transforms complex, repetitive AI interactions into persistent, executable scripts that can be managed, version controlled, and reused across sessions.
Installation
NPX
npx scriptflow-mcp
Configuration
Claude Desktop
{
"mcpServers": {
"scriptflow": {
"command": "npx",
"args": ["scriptflow-mcp"],
"env": {
"SCRIPTFLOW_SCRIPTS_DIR": "/your/custom/path"
}
}
}
}
Available Tools
| Tool | Description |
|---|---|
script_add |
Add a new script (name, description, content, language, tags) |
script_edit |
Update an existing script |
script_get |
View script details |
script_list |
Search/filter scripts |
script_run |
Execute a script with arguments |
script_rm |
Delete a script |
Features
- Transform successful AI interactions into reusable, executable scripts
- Save time and tokens by executing complex tasks instantly
- Guaranteed consistency — scripts execute the same way every time
- Search, organize, edit, and version control your automation library
- Team collaboration — share proven workflows across your organization
- Add/edit/delete scripts with metadata
- List/search scripts by name, description, or tags
- Execute scripts with arguments
- Support for multiple languages (Bash, Python, Node.js, TypeScript)
Environment Variables
Optional
SCRIPTFLOW_SCRIPTS_DIR- Scripts directory (default: /tmp/scriptflow-mcp/scripts)SCRIPTFLOW_TIMEOUT- Execution timeout in ms (default: 30000)
Usage Examples
Add a script with name 'hello', description 'Hello script', and content 'echo 'Hello!''
Run the 'hello' script with argument 'World'
List scripts and search for 'hello'
Notes
Scripts are saved as {name}.{ext} + {name}.json files with metadata. Supports Bash (.sh), Python (.py), JavaScript (.js), TypeScript (.ts). Can be tested with MCP Inspector using: npx @modelcontextprotocol/inspector npx scriptflow-mcp