Skip to main content
Glama

MCP Server Proto-OKN

by sbl-sdsc

MCP Server Proto-OKN

A Model Context Protocol (MCP) server that provides tools for querying SPARQL endpoints, with specialized support for Proto-OKN (Prototype Open Knowledge Network) knowledge graphs hosted on the FRINK platform.

Features

  • FRINK Integration: Automatic detection and documentation linking for FRINK-hosted knowledge graphs
  • Proto-OKN Support: Optimized for querying knowledge graphs in the Proto-OKN ecosystem including:
    • SPOKE (Scalable Precision Medicine Open Knowledge Engine)
    • BioBricks ICE (Chemical safety and cheminformatics)
    • DREAM-KG (Addressing homelessness with explainable AI)
    • SAWGraph (Safe Agricultural Products and Water monitoring)
    • And many other Proto-OKN knowledge graphs
  • Flexible Configuration: Support for both FRINK and custom SPARQL endpoints
  • Automatic Documentation: Registry links for supported knowledge graphs

Installation

Prerequisites

  1. Install VS Code Insiders (required for MCP support)Download and install VS Code Insiders from https://code.visualstudio.com/insiders/VS Code Insiders is needed because it includes the latest MCP (Model Context Protocol) features.
  2. Install GitHub Copilot extension (required for MCP integration)
    • Open VS Code Insiders
    • Install the GitHub Copilot extension from the marketplace
    • Sign in with your GitHub account that has Copilot access
    • Note: You need an active GitHub Copilot subscription to use MCP features

    MCP servers integrate with VS Code through the Copilot Chat interface.

  3. Install uv (Python package manager)
    # macOS/Linux curl -LsSf https://astral.sh/uv/install.sh | sh # Windows powershell -c "irm https://astral.sh/uv/install.ps1 | iex" # Or via pip pip install uv

Setup Instructions

  1. Clone and setup the project
    git clone https://github.com/sbl-sdsc/mcp-proto-okn.git cd mcp-proto-okn uv sync
  2. Configure the MCP serversThis project includes a pre-configured .vscode/mcp.json file with multiple Proto-OKN knowledge graph endpoints. You need to update the commands to use the new mcp-server-protookn:Edit .vscode/mcp.json and update the server configurations:
    { "servers": { "mcp-spoke-sparql": { "command": "uv", "args": ["run", "python", "-m", "mcp_server_protookn.server", "--endpoint", "https://frink.apps.renci.org/spoke/sparql"] }, "mcp-dreamkg-sparql": { "command": "uv", "args": ["run", "python", "-m", "mcp_server_protookn.server", "--endpoint", "https://frink.apps.renci.org/dreamkg/sparql"] } } }
    The existing file contains configurations for all major Proto-OKN knowledge graphs. You can enable/disable specific servers by adding or removing them from the configuration.
  3. Start using the MCP server
    • Open VS Code Insiders
    • Open a new chat window
    • The MCP servers should automatically connect and provide access to the knowledge graphs

Quick Start: Query a Knowledge Graph

Once everything is set up, you can start querying knowledge graphs through the VS Code chat interface:

Example prompts to try:

  1. Explore the SPOKE knowledge graph structure:
    What types of entities are available in the SPOKE knowledge graph?
  2. Query that combines multiple entity types:
    Antibiotic contamination can contribute to antimicrobial resistance. Find locations with antibiotic contamination.
  3. Query across multiple KGs:
    What type of data is available for perfluorooctanoic acid in SPOKE, BioBricks, and SAWGraph?

The chat interface will use the MCP server to execute SPARQL queries against the configured endpoints and return structured results.

Alternative Installation Methods

Using uvx (standalone execution)
uvx mcp-server-protookn --endpoint https://frink.apps.renci.org/spoke/sparql

Usage

Command Line Parameters

The MCP server accepts the following command line arguments:

Required:

  • --endpoint: SPARQL endpoint URL (e.g., https://frink.apps.renci.org/spoke/sparql)

Optional:

  • --description: Custom description for the SPARQL endpoint (automatically generated for FRINK endpoints)

Command Line

# FRINK endpoint (automatic documentation linking) uvx mcp-server-protookn --endpoint https://frink.apps.renci.org/spoke/sparql # Custom endpoint with description uvx mcp-server-protookn --endpoint https://example.com/sparql --description "Custom SPARQL endpoint"

Tool: query

Execute a SPARQL query against the configured endpoint.

Parameters:

  • query_string: A valid SPARQL query string
  • description: Custom description for the SPARQL endpoint (automatically generated for FRINK endpoints)

Returns:

  • The query results in JSON format
-
security - not tested
A
license - permissive license
-
quality - not tested

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

A Model Context Protocol server that provides tools for querying SPARQL endpoints, with specialized support for Proto-OKN knowledge graphs hosted on the FRINK platform.

  1. Features
    1. Installation
      1. Prerequisites
      2. Setup Instructions
      3. Quick Start: Query a Knowledge Graph
      4. Alternative Installation Methods
    2. Usage
      1. Command Line Parameters
      2. Command Line
    3. Tool: query
      1. Links

        Related MCP Servers

        • -
          security
          A
          license
          -
          quality
          A Model Context Protocol server that enables LLMs to interact with GraphQL APIs by providing schema introspection and query execution capabilities.
          Last updated -
          469
          1
          MIT License
          • Apple
        • -
          security
          F
          license
          -
          quality
          A Model Context Protocol server that enables LLMs to interact with GraphQL APIs by providing schema introspection and query execution capabilities.
          Last updated -
          1
          TypeScript
          • Apple
          • Linux
        • A
          security
          A
          license
          A
          quality
          A Model Context Protocol server that provides read-only access to Ontotext GraphDB, enabling LLMs to explore RDF graphs and execute SPARQL queries.
          Last updated -
          2
          8
          JavaScript
          GPL 3.0
        • -
          security
          A
          license
          -
          quality
          A Model Context Protocol server for MarkLogic that enables CRUD operations and document querying capabilities through a client interface.
          Last updated -
          Python
          MIT License

        View all related MCP servers

        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/sbl-sdsc/mcp-proto-okn'

        If you have feedback or need assistance with the MCP directory API, please join our Discord server