ISPW MCP Server
Enables LLMs to manage mainframe source code and deployment workflows via BMC Compuware ISPW, supporting assignment, task, release, and deployment operations.
README
ISPW MCP Server
A Model Context Protocol (MCP) server for BMC Compuware ISPW (Interactive Source Program Workbench) - a comprehensive source code management, release automation, and deployment automation tool for mainframe DevOps.
Overview
This MCP server enables LLMs to interact with ISPW through a comprehensive set of tools for:
- Assignment Management: Create, list, and retrieve assignments (containers for development work)
- Task Management: View tasks within assignments (individual modules/components)
- Release Management: Create and manage releases for coordinated deployments
- Operations: Generate, promote, and deploy code through the development lifecycle
- Set & Package Management: List and view deployment sets and packages
Features
- ✅ Complete ISPW REST API coverage for core workflows
- ✅ Token-based authentication with CES (Compuware Enterprise Services)
- ✅ Dual output formats: Human-readable Markdown and machine-readable JSON
- ✅ Comprehensive error handling with actionable messages
- ✅ Pydantic validation for all inputs
- ✅ Async/await for optimal performance
- ✅ Support for both production and custom CES servers
Installation
Prerequisites
- Python 3.10 or higher
- Access to a BMC Compuware ISPW instance
- Personal Access Token for CES authentication
Setup
-
Clone or create the project directory:
cd /path/to/ispw-mcp-server -
Create and activate a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install dependencies:
pip install -e . -
Configure environment variables:
cp .env.example .envEdit
.envand set your values:# For custom CES server: CES_HOST=your-ces-host.example.com CES_PORT=2020 # Or for production server: # ISPW_BASE_URL=https://ispw.api.compuware.com # Required: Your personal access token ISPW_API_TOKEN=your_token_here # Default SRID (optional, defaults to "ISPW") ISPW_DEFAULT_SRID=ISPW
Usage
Running the Server
As a standalone script:
python ispw_mcp_server.py
Using the installed command:
ispw-mcp-server
With the MCP Inspector (for testing):
npx @modelcontextprotocol/inspector python ispw_mcp_server.py
Configuration in Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"ispw": {
"command": "python",
"args": ["/path/to/ispw-mcp-server/ispw_mcp_server.py"],
"env": {
"ISPW_BASE_URL": "https://your-ces-host:2020",
"ISPW_API_TOKEN": "your_token_here",
"ISPW_DEFAULT_SRID": "ISPW"
}
}
}
}
Or using a virtual environment:
{
"mcpServers": {
"ispw": {
"command": "/path/to/ispw-mcp-server/venv/bin/python",
"args": ["/path/to/ispw-mcp-server/ispw_mcp_server.py"],
"env": {
"ISPW_BASE_URL": "https://your-ces-host:2020",
"ISPW_API_TOKEN": "your_token_here",
"ISPW_DEFAULT_SRID": "ISPW"
}
}
}
}
Available Tools
Assignment Tools
ispw_list_assignments
List all assignments for a specific SRID, with optional filtering by level or assignment ID.
Parameters:
srid(str): System Resource Identifier (default: from env)level(optional): Filter by level (DEV, INT, ACC, PRD)assignment_id(optional): Filter by specific assignment IDresponse_format(optional): "markdown" or "json" (default: markdown)
Example:
List all DEV level assignments for SRID ISPW
ispw_get_assignment
Get detailed information about a specific assignment.
Parameters:
srid(str): System Resource Identifierassignment_id(str): Assignment identifierresponse_format(optional): Output format
Example:
Get details for assignment PLAY000001 in ISPW
ispw_create_assignment
Create a new assignment.
Parameters:
srid(str): System Resource Identifierassignment_id(str): Unique assignment identifierstream(str): Stream nameapplication(str): Application namedescription(optional): Assignment descriptiondefault_path(optional): Default pathresponse_format(optional): Output format
Example:
Create a new assignment PLAY000002 in ISPW for stream PLAY and application PLAY
Task Tools
ispw_list_tasks
List all tasks for a specific assignment.
Parameters:
srid(str): System Resource Identifierassignment_id(str): Assignment identifierresponse_format(optional): Output format
Example:
List all tasks for assignment PLAY000001
Release Tools
ispw_list_releases
List all releases for a specific SRID.
Parameters:
srid(str): System Resource Identifierrelease_id(optional): Filter by specific release IDresponse_format(optional): Output format
Example:
List all releases for ISPW
ispw_get_release
Get detailed information about a specific release.
Parameters:
srid(str): System Resource Identifierrelease_id(str): Release identifierresponse_format(optional): Output format
ispw_create_release
Create a new release.
Parameters:
srid(str): System Resource Identifierrelease_id(str): Unique release identifierstream(str): Stream nameapplication(str): Application namedescription(optional): Release descriptionresponse_format(optional): Output format
Operation Tools
ispw_generate_assignment
Generate code for an assignment (compile and prepare).
Parameters:
srid(str): System Resource Identifierassignment_id(str): Assignment identifierlevel(optional): Target level for generationruntime_configuration(optional): Runtime configurationresponse_format(optional): Output format
Example:
Generate assignment PLAY000001 for level DEV
ispw_promote_assignment
Promote an assignment to the next level.
Parameters:
srid(str): System Resource Identifierassignment_id(str): Assignment identifierlevel(optional): Target level for promotionchange_type(optional): S (Standard), I (Incidental), E (Emergency)execution_status(optional): Execution statusresponse_format(optional): Output format
Example:
Promote assignment PLAY000001 to INT level with Standard change type
ispw_deploy
Deploy an assignment, release, or set to target environment.
⚠️ CAUTION: This is a destructive operation that affects production or target environments.
Parameters:
srid(str): System Resource Identifiertarget_id(str): Assignment, release, or set identifiertarget_type(str): "assignment", "release", or "set"level(optional): Target level for deploymentdeploy_implementation_time(optional): Scheduled time (ISO 8601)deploy_active(optional): Deploy to active libraries (boolean)response_format(optional): Output format
Examples:
Deploy assignment PLAY000001 to production
Deploy release REL001 to PRD level
Schedule deployment of assignment PLAY000001 for 2026-01-15T10:00:00Z
Set and Package Tools
ispw_list_sets
List all sets for a specific SRID.
Parameters:
srid(str): System Resource Identifierset_id(optional): Filter by specific set IDresponse_format(optional): Output format
ispw_list_packages
List all packages for a specific SRID.
Parameters:
srid(str): System Resource Identifierpackage_id(optional): Filter by specific package IDresponse_format(optional): Output format
ispw_get_package
Get detailed information about a specific package.
Parameters:
srid(str): System Resource Identifierpackage_id(str): Package identifierresponse_format(optional): Output format
Architecture
Key Design Decisions
- Comprehensive API Coverage: Implements all major ISPW REST API endpoints for complete workflow support
- Dual Format Responses: Markdown for human readability, JSON for programmatic processing
- Shared Utilities: DRY principle with reusable API client, error handling, and formatting functions
- Strong Validation: Pydantic models ensure all inputs are validated before API calls
- Async Design: All I/O operations use async/await for optimal performance
- Flexible Configuration: Support for both production and custom CES servers
Project Structure
ispw-mcp-server/
├── ispw_mcp_server.py # Main server implementation
├── ispw_openapi_spec.json # OpenAPI specification (reference)
├── pyproject.toml # Project configuration
├── .env.example # Environment template
├── .env # Your configuration (not in git)
├── .gitignore # Git ignore rules
└── README.md # This file
Development
Running Tests
pytest
Code Quality
The project uses Ruff for linting:
ruff check .
Adding New Tools
When adding new ISPW API endpoints:
- Define Pydantic input model with validation
- Create tool function with
@mcp.tool()decorator - Add proper annotations (readOnlyHint, destructiveHint, etc.)
- Implement using shared
_make_api_request()utility - Handle errors with
_handle_api_error() - Support both markdown and JSON output formats
- Update this README with tool documentation
Troubleshooting
Authentication Errors
Problem: "Error: Authentication failed. Check your ISPW_API_TOKEN is valid."
Solution:
- Verify your Personal Access Token is correct
- Ensure the token has appropriate permissions in CES
- Check token hasn't expired
Connection Errors
Problem: "Error: Request timed out. The ISPW server may be slow or unavailable."
Solution:
- Verify CES_HOST and CES_PORT are correct
- Check network connectivity to the CES server
- Increase ISPW_TIMEOUT if operations are legitimately slow
SSL Certificate Issues
Problem: SSL certificate verification fails for custom CES server
Solution: The server currently disables SSL verification for custom CES servers. For production use, configure proper SSL certificates.
Security Considerations
- Token Management: Store ISPW_API_TOKEN securely, never commit to version control
- SSL Verification: Consider enabling SSL verification for production deployments
- Access Control: Tokens should have minimal required permissions
- Audit Logging: ISPW maintains audit logs of all operations
Contributing
When contributing:
- Follow Python best practices and PEP 8
- Use type hints throughout
- Add comprehensive docstrings
- Include parameter validation
- Test with both markdown and JSON formats
- Update README documentation
License
[Specify your license here]
Support
For ISPW API issues, consult:
- BMC Compuware ISPW documentation
- BMC Compuware Support: https://www.bmc.com/support/
For MCP server issues:
- Check server logs
- Test with MCP Inspector
- Review environment configuration
Changelog
Version 1.0.0 (2026-01-08)
Initial release with:
- Complete assignment lifecycle management
- Task viewing capabilities
- Release creation and management
- Generate, promote, and deploy operations
- Set and package listing
- Dual output formats (Markdown/JSON)
- Comprehensive error handling
- Full Pydantic validation
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.