Skip to main content
The Knowledge Graph MCP Server implements the Model Context Protocol ↗ for K-12 educational data. Instead of relying on model recall, the MCP Server relies on tools ↗ and structured Knowledge Graph data to:

What you’ll need

  • MCP Server URL:
  • API keys generated in the Learning Commons Platform ↗ to include in your request headers for authentication:
    or
    If using an SDK, verify how to pass in the MCP authorization key for your client.

Steps

1

Set up environment variables

.env
2

Connect to the MCP server

Make a request to the MCP server with your question — for example, asking about skills and unfinished learning for California standard 4.OA.A.3:
3

Review the response

Your AI client will call Knowledge Graph MCP tools to return structured results (e.g., Academic Standard statements, Learning Components, or Learning Progressions).Inspect mcp_call output entries for tool names, arguments, and results.

Tools

Please review the Knowledge Graph License before using these tools.
The MCP server contains the following tools ↗, which can be used individually or in sequence:
A common workflow may use all 3 tools:
  • Resolving a standard code to its official statement
  • Retrieving the associated learning components for targeted instruction
  • Tracing progressions to identify prior or follow-on standards

Inputs

ToolFieldTypeRequiredDescription
Find Academic Standard statementstatementCodestringe.g., RI.5.2 or 8.F.B.4
jurisdictionstringJurisdiction where standard is adopted (e.g., Maryland)
Find Learning Components from standardcaseIdentifierUUIDstringUUID of the standard in the CASE Network
Find Learning Progressions from standardcaseIdentifierUUIDstringUUID of the standard in the CASE Network
directionstringbackward for prerequisites and forward for subsequent

Quickstart

Set up MCP access and try your first Knowledge Graph requests.