siemens-graph-studio-mcp-server 0.5.1

An MCP server for Altair Graph Studio (AGS) providing intelligent SPARQL query capabilities via the Model Context Protocol.

RMGS MCP Server

An MCP (Model Context Protocol) server for Altair Graph Studio (AGS) that provides intelligent SPARQL query capabilities, ontology management, and graphmart construction tools — all accessible from AI coding assistants like GitHub Copilot, Claude Desktop, and other MCP-compatible clients.

Features

• SPARQL Query Execution — Run SPARQL queries against AGS graphmarts
• Knowledge Discovery — Explore ontologies, classes, and properties
• Ontology Management — Create, modify, and delete ontologies
• Graphmart Construction — Build and manage transformation layers and steps
• Agent Memory — Persistent and ephemeral memory for context retention
• Dual Modes — explore (read-only, 8 tools) and create (all 40+ tools)
• Multiple Transports — stdio, SSE, and streamable-http

Installation

From PyPI

pip install siemens-graph-studio-mcp-server

Note: Installing this package will also install rdflib, which adds rdfpipe and rdfgraphisomorphism executables to your environment. These are standard rdflib CLI utilities and are not part of this MCP server — they can be safely ignored.

From Source

git clone [e-mail]:boris.shalumov/rmgs-mcp-server.git
cd rmgs-mcp-server
pip install -e .

Development Install

pip install -e ".[dev]"

Configuration

The server requires the following environment variables:

Variable	Description	Required
ANZO_SERVER	AGS server hostname	Yes
ANZO_PORT	AGS server port	Yes
ANZO_USERNAME	Anzo username	Yes
ANZO_PASSWORD	Anzo password	Yes
GRAPHMART_URI	Graphmart URI	Yes
API_KEY	OpenAI API key (only needed for LLM-powered features)	No
ENABLE_AGENT_DEBUG	Enable agent debug logs (true/false)	No
ENABLE_LOGGING_DEBUG	Enable verbose logging (true/false)	No

You can also pass a JSON/JSONC config file with --config:

siemens-graph-studio-mcp-server --config config/connection.json

Example config file (config/connection.json):

{
  "anzo_server": "your-ags-server",
  "anzo_port": 443,
  "anzo_username": "user",
  "anzo_password": "password",
  "graphmart_uri": "http://cambridgesemantics.com/Graphmart/your-id",
  "api_key": "sk-...",
  "mcp_transport": "stdio"
}

Usage

Run as CLI

# stdio transport (default)
siemens-graph-studio-mcp-server

# With config file
siemens-graph-studio-mcp-server --config config/connection.json

# SSE transport
siemens-graph-studio-mcp-server --transport sse --port 8000

# Streamable HTTP
siemens-graph-studio-mcp-server --transport streamable-http --host 0.0.0.0 --port 8000

# Explore mode (read-only tools only)
siemens-graph-studio-mcp-server --mode explore

# Create mode (all tools)
siemens-graph-studio-mcp-server --mode create

Run as Python module

python -m rmgs_mcp_server.ags_sparql_agent --config config/connection.json

VS Code Integration

Option 1: Install from PyPI (Recommended)

1. Install the package in your Python environment:

   pip install siemens-graph-studio-mcp-server
   

2. Add the MCP server to your VS Code settings. Create or edit .vscode/mcp.json in your workspace:

   {
     "servers": {
       "siemens-graph-studio-mcp-server": {
         "type": "stdio",
         "command": "siemens-graph-studio-mcp-server",
         "args": ["--config", "/path/to/your/connection.json"]
       }
     }
   }
   

   Or with inline environment variables:

   {
     "servers": {
       "siemens-graph-studio-mcp-server": {
         "type": "stdio",
         "command": "siemens-graph-studio-mcp-server",
         "args": [],
         "env": {
           "ANZO_SERVER": "your-ags-server",
           "ANZO_PORT": "443",
           "ANZO_USERNAME": "your-username",
           "ANZO_PASSWORD": "your-password",
           "GRAPHMART_URI": "http://cambridgesemantics.com/Graphmart/your-id",
           "API_KEY": "your-openai-api-key"
         }
       }
     }
   }
   

3. Reload VS Code. The MCP server will appear in your Copilot Chat tool list.

Option 2: Run from Source

1. Clone and install in editable mode:

   git clone [e-mail]:boris.shalumov/rmgs-mcp-server.git
   cd rmgs-mcp-server
   pip install -e .
   

2. Use the same .vscode/mcp.json configuration as Option 1.

Option 3: Direct Python Execution (No Install)

If you prefer not to install the package, point directly to the script:

{
  "servers": {
    "siemens-graph-studio-mcp-server": {
      "type": "stdio",
      "command": "python",
      "args": ["/absolute/path/to/rmgs-mcp-server/rmgs_mcp_server/ags_sparql_agent.py"],
      "env": {
        "PYTHONPATH": "/absolute/path/to/rmgs-mcp-server",
        "ANZO_SERVER": "your-ags-server",
        "ANZO_PORT": "443",
        "ANZO_USERNAME": "your-username",
        "ANZO_PASSWORD": "your-password",
        "GRAPHMART_URI": "http://cambridgesemantics.com/Graphmart/your-id",
        "API_KEY": "your-openai-api-key"
      }
    }
  }
}

Using with VS Code Copilot Chat

Once configured, the MCP tools are available in GitHub Copilot Chat (Agent mode). You can:

• Ask questions about your knowledge graph data
• Discover ontologies and their structure
• Execute SPARQL queries
• Create and manage graphmart transformation layers
• Build and modify ontologies

Example prompts:

• "What ontologies are available in this graphmart?"
• "Show me the classes in the automotive ontology"
• "Run a SPARQL query to find all vehicles with more than 200 horsepower"
• "Create a new transformation layer for data enrichment"

Claude Desktop Integration

Add to ~/.config/claude-desktop/claude_desktop_config.json:

{
  "mcpServers": {
    "siemens-graph-studio-mcp-server": {
      "command": "siemens-graph-studio-mcp-server",
      "args": ["--config", "/path/to/connection.json"],
      "env": {}
    }
  }
}

Tool Categories

System & Monitoring

Tool	Description
test_system_connection	Test MCP server and AGS agent status
get_session_logs	Get session logs and interaction history

SPARQL Query Execution

Tool	Description
execute_sparql_query	Execute SPARQL directly against graphmart
query_ags_configuration	Query graphmart metadata (local volume)
update_ags_configuration	Update graphmart metadata with SPARQL

Knowledge Discovery

Tool	Description
discover_knowledge_overview	Get overview of available knowledge
discover_available_ontologies	List all available ontologies
discover_ontology_classes	List classes in a specific ontology
discover_class_data_properties	List data properties for a class
discover_class_object_properties	List object properties for a class

Ontology Management

Tool	Description
create_ontology	Create a new ontology
delete_ontology	Delete an ontology
register_ontology	Register ontologies
load_ontology_from_file	Load TTL files into named graphs
add_ontology_class	Add a class to an ontology
remove_ontology_class	Remove a class from an ontology
add_ontology_property	Add a property to an ontology
remove_ontology_property	Remove a property from an ontology
add_ontology_import	Add an import to an ontology
remove_ontology_import	Remove an import from an ontology
list_ontology_structure_classes	List classes in ontology structure
list_ontology_structure_properties	List properties in ontology structure
get_ontology_cache_status	Get ontology cache status
clear_ontology_cache	Clear ontology caches
refresh_ontology_cache	Force cache refresh

Graphmart Construction

Tool	Description
create_transformation_layer	Create transformation layers
update_transformation_layer	Update layer properties
delete_transformation_layer	Delete transformation layers
list_transformation_layers	List all transformation layers
add_transformation_step	Add transformation steps to layers
update_transformation_step	Update transformation step properties
delete_transformation_step	Delete transformation steps
list_transformation_steps	List steps within a layer
add_direct_load_step	Add direct data loading steps
update_direct_load_step	Update direct load step properties
refresh_graphmart	Lightweight refresh of changed layers
reload_graphmart	Complete reprocessing of all layers
get_layer_status	Comprehensive layer and step error info
get_step_status	Specific step debugging

Agent Memory

Tool	Description
initialize_agent_memory	Initialize memory for the agent
write_permanent_memory	Write to persistent memory
write_ephemeral_memory	Write to session-scoped memory
promote_ephemeral_memory	Promote ephemeral to permanent memory
clear_agent_memory	Clear agent memory
read_agent_memory	Read from agent memory

Publishing to PyPI

Build

pip install build twine
python -m build

This creates dist/rmgs_mcp_server-<version>.tar.gz and dist/rmgs_mcp_server-<version>-py3-none-any.whl.

Upload to PyPI

# Test PyPI (recommended first)
twine upload --repository testpypi dist/*

# Production PyPI
twine upload dist/*

Bump Version

Update the version in both:

• pyproject.toml → version = "x.y.z"
• rmgs_mcp_server/__init__.py → __version__ = "x.y.z"

Development

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest

# Build package
python -m build

Project Structure

rmgs-mcp-server/
├── rmgs_mcp_server/           # Main package
│   ├── __init__.py            # Package init with version
│   ├── ags_sparql_agent.py    # MCP server entry point
│   ├── models.py              # Pydantic/dataclass models
│   ├── sparql_agent_core.py   # Core SPARQL agent logic
│   ├── sparql_query_engine.py # SPARQL query engine
│   ├── ontology_cache.py      # Ontology caching
│   ├── ontology_discovery.py  # Ontology discovery
│   ├── interaction_logger.py  # Logging utilities
│   ├── tools/                 # MCP tool implementations
│   │   ├── base_tool.py       # Base tool class
│   │   ├── system/            # System & monitoring tools
│   │   ├── query/             # SPARQL query tools
│   │   ├── discovery/         # Knowledge discovery tools
│   │   ├── ontology/          # Ontology management tools
│   │   ├── graphmart/         # Graphmart construction tools
│   │   └── memory/            # Agent memory tools
│   └── utils/                 # Shared utilities
├── config/                    # Configuration templates
├── prompts/                   # Agent prompt templates
├── skills/                    # Best practices guides
├── pyproject.toml             # Package metadata & build config
├── LICENSE                    # MIT License
└── README.md                  # This file

License

MIT