OSOP MCP Server
Enables importing GitHub Actions workflows into the OSOP format and exporting OSOP workflows to external formats including GitHub Actions.
Allows rendering OSOP workflows as Mermaid diagrams for visualization and documentation.
Supports rendering OSOP workflows as SVG diagrams for high-quality graphical representations.
Provides capabilities to validate OSOP workflow definitions stored in YAML format against the OSOP schema.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OSOP MCP ServerConvert my main.yml GitHub Action into an OSOP workflow"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OSOP MCP Server
5 tools for AI agents to validate, record, diff, optimize, and view OSOP workflows.
Any MCP-compatible client (Claude, Cursor, Windsurf) becomes workflow-aware.
Tools
Tool | Description |
| Validate |
| Execute workflow, produce |
| Compare two workflows or execution logs |
| Synthesize better workflow from multiple execution logs |
| Render |
Installation
pip install osop-mcpUsage
Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"osop": {
"command": "python",
"args": ["-m", "osop_mcp"]
}
}
}Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"osop": {
"command": "python",
"args": ["-m", "osop_mcp"],
"env": {}
}
}
}What is OSOP?
OSOP is the standard format for describing and logging AI agent workflows. 4 node types, 4 edge modes.
CLI:
pip install osop(validate, record, diff, optimize, view)Spec: osop-spec
Editor: osop-editor
License
Apache License 2.0
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Archie0125/osop-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server