Skip to main content

Early access
Early access features and functionality are actively evolving, and breaking changes may occur as we expand capabilities and improve accuracy and reliability. Email support@learningcommon.org with your feedback or issues.
The Model Context Protocol (MCP) is an open-source standard for connecting AI applications to external systems. MCP servers expose tools that allow AI models to perform actions (always with user approval). Each tool defines a specific operation with typed inputs and outputs, and the model requests tool execution based on conversation context. The Knowledge Graph MCP Server implements the Model Context Protocol in the K12 education domain. It provides tools for working with the academic standards, learning components, and learning progressions represented in the Knowledge Graph. These tools allow AI models to reliably resolve standards, decompose them into granular learning components, and trace progressions across standards—all through structured, authoritative data rather than relying on model recall.

​
Server URL

https://kg.mcp.learningcommons.org/mcp

​
Authentication

The Knowledge Graph MCP server uses API keys for authentication. You can create and manage API keys in the Learning Commons Platform. x-api-key: YOUR_API_KEY or Authorization: Bearer YOUR_API_KEY
If using an SDK, such as OpenAI or Anthropic, please check the correct way to pass the MCP auth key

​
Example usage

# .env file:
# OPENAI_API_KEY=sk-...
# MCP_AUTH_KEY=your_kg_api_key
# MCP_SERVER_URL=https://kg.mcp.learningcommons.org/mcp

import os
import requests
from dotenv import load_dotenv

load_dotenv()

openai_api_key = os.getenv("OPENAI_API_KEY")
mcp_server_url = os.getenv("MCP_SERVER_URL")
mcp_auth_key   = os.getenv("MCP_AUTH_KEY")

input_prompt = "I am a 4th grade teacher in California. A new student in my class is struggling with the concepts related to 4.OA.A.3. What are the skills required for mastery and what potential unfinished learning should I address?."

response = requests.post(
    "https://api.openai.com/v1/responses",
    headers={
        "Content-Type":  "application/json",
        "Authorization": f"Bearer {openai_api_key}",
    },
    json={
        "model": "gpt-4o",
        "tools": [
            {
                "type": "mcp",
                "server_label": "learning-commons-kg",
                "server_url": mcp_server_url,
                "require_approval": "never",
                "headers": {
                    "x-api-key": mcp_auth_key
                }
            }
        ],
        "input": input_prompt
    }
)

print(response.status_code)
for item in response.json()["output"]:
    if item["type"] == "mcp_call":
        print(f"Tool called: {item['name']}")
        print(f"Arguments:   {item['arguments']}")
        print(f"Result:      {item['output']}")
    elif item["type"] == "message":
        print(f"Answer: {item['content'][0]['text']}")

​
Knowledge Graph MCP tools

  • Find standard statement: Resolves an education standard code into its authoritative statement and metadata, optionally scoped to a jurisdiction.
  • Find learning components from standard: Breaks a standard into granular learning components that represent individual, teachable skills.
  • Find learning progressions from standard: Identifies prior or subsequent standards in a learning progression, based on the Student Achievement Partners (SAP) Coherence Map for Mathematics.
These tools can be used individually or in sequence. For example, a workflow may begin by resolving a standard code into its official statement, then retrieve the associated learning components for targeted instruction, and finally, trace progressions to identify prior or follow-on standards.
Please review the Knowledge Graph License before using these tools.

​
Find standard statement

Resolves an education standard code into its official statement and metadata.
Input
FieldTypeRequiredDescription
statementCodestringYesShort code identifying the standard (e.g., RI.5.2 or 8.F.B.4).
jurisdictionstringNoJurisdiction where the standard is adopted (e.g., Maryland). Optional.

​
Find learning components from standard

Breaks down a broad standard into specific, granular learning components that represent individual teachable skills.
Input
FieldTypeRequiredDescription
caseIdentifierUUIDstringYesUUID of the standard in the CASE Network (from Find standard statement).

​
Find learning progressions from standard

Identifies prerequisite or subsequent standards in a learning progression, based on the Student Achievement Partners (SAP) Coherence Map for Mathematics.
Input
FieldTypeRequiredDescription
caseIdentifierUUIDstringYesUUID of the standard in the CASE Network (from Find standard statement).
directionstringYesTraversal direction: backward (prerequisites) or forward (subsequent).