The Ontology MCP server connects GraphDB's SPARQL endpoint with various AI models (Ollama, OpenAI, Gemini), serving as a Model Context Protocol server for Claude.
SPARQL Operations:
Execute queries and updates on GraphDB repositories
List repositories and named graphs
Retrieve resource information by URI
Ollama Integration:
Run, download, list and delete models
Perform chat completions
Check server status
OpenAI Features:
Execute chat completions
Generate images via DALL-E
Text-to-speech and speech-to-text conversion
Generate text embeddings
Gemini AI:
Generate text and chat completions
List available models
Image/video generation capabilities (some currently disabled)
HTTP Requests:
Execute GET, POST, PUT, DELETE, and PATCH requests to external APIs
Data Management:
Import RDF data into GraphDB repositories
Manage ontologies
Uses Docker to run GraphDB and provide SPARQL endpoint functionality
Provides access to Gemini models for text generation, chat completion, and model listing with support for various Gemini model variants
Enables running, managing, and interacting with Ollama models including execution, information retrieval, downloading, listing, deletion, and chat completion
Provides access to OpenAI services including chat completion, image generation, text-to-speech, speech-to-text, and embedding generation
Ontology MCP is a Model Context Protocol (MCP) server that connects GraphDB's SPARQL endpoints and Ollama models to Claude. This tool allows Claude to query and manipulate ontology data and leverage various AI models.
Execute SPARQL query ( mcp_sparql_execute_query )
Execute SPARQL update query ( mcp_sparql_update )
List repositories ( mcp_sparql_list_repositories )
Query the graph list ( mcp_sparql_list_graphs )
Get resource information ( mcp_sparql_get_resource_info )
Run the model ( mcp_ollama_run )
Check model information ( mcp_ollama_show )
Download model ( mcp_ollama_pull )
Get model list ( mcp_ollama_list )
Delete model ( mcp_ollama_rm )
Chat completion ( mcp_ollama_chat_completion )
Check container status ( mcp_ollama_status )
Chat completed ( mcp_openai_chat )
Create image ( mcp_openai_image )
Text-to-speech ( mcp_openai_tts )
Speech-to-text ( mcp_openai_transcribe )
Generate embedding ( mcp_openai_embedding )
Generate text ( mcp_gemini_generate_text )
Chat completion ( mcp_gemini_chat_completion )
Get model list ( mcp_gemini_list_models )
~~Generate images ( mcp_gemini_generate_images ) - Using Imagen model~~ (currently disabled)
~~Generate videos ( mcp_gemini_generate_videos ) - Using Veo models~~ (currently disabled)
~~Generate multimodal content ( mcp_gemini_generate_multimodal_content )~~ (currently disabled)
Note : Gemini's image creation, video creation, and multimodal content creation features are currently disabled due to API compatibility issues.
Model transformation | input | output of power | Optimization Goal |
Gemini 2.5 Flash Preview
| Audio, images, video, text | Text | Adaptive thinking, cost-effectiveness |
Gemini 2.5 Pro Preview
| Audio, images, video, text | Text | Enhanced thinking and reasoning, multimodal understanding, advanced coding |
Gemini 2.0 Flash
| Audio, images, video, text | Text, images (experimental), audio (coming soon) | Next-generation capabilities, speed, thinking, real-time streaming, multimodal creation |
Gemini 2.0 Flash-Lite
| Audio, images, video, text | Text | Cost-effective and low latency |
Gemini 1.5 Flash
| Audio, images, video, text | Text | Fast and versatile performance for a variety of tasks |
Gemini 1.5 Flash-8B
| Audio, images, video, text | Text | High volume and low intelligence tasks |
Gemini 1.5 Pro
| Audio, images, video, text | Text | Complex reasoning tasks that require more intelligence |
Gemini embedding
| Text | Text embedding | Measuring the relevance of text strings |
Imagen 3
| Text | image | Google's most advanced image generation model |
Veo 2
| Text, Images | video | Create high-quality videos |
Gemini 2.0 Flash Live
| Audio, video, text | Text, Audio | Low-latency, two-way voice and video interaction |
Execute HTTP requests ( mcp_http_request ) - communicate with external APIs using various HTTP methods such as GET, POST, PUT, DELETE, etc.
Start the GraphDB server by running the following command from the project root directory:
The GraphDB web interface runs at http://localhost:7200 .
Go to the GraphDB web interface ( http://localhost:7200 ) and do the following:
Create a repository:
“Setup” → “Repositories” → “Create new repository”
Repository ID: schemaorg-current-https (or whatever name you want)
Repository title: "Schema.org"
Click "Create"
Get sample data:
Select the repository you created
“Import” → “RDF” → “Upload RDF files”
Upload an example file to the imports directory (e.g. imports/example.ttl )
Click "Import"
Note : The project includes example RDF files in the
importsdirectory.
To use Ontology MCP in Claude Desktop, you need to update the MCP settings file:
Open the Claude Desktop settings file:
Windows: %AppData%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Add the following settings:
IMPORTANT : Change the path in `args' to the actual absolute path to your project build directory.
Restart Claude Desktop
This project is provided under the MIT License. See the LICENSE file for details.
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
A Model Context Protocol (MCP) server that connects GraphDB's SPARQL endpoints and Ollama models to Claude, enabling Claude to query and manipulate ontology data while leveraging various AI models.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bigdata-coss/agent_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server