Quickstart

Using Knowledge Graph

You can access Knowledge Graph data in several ways:

Access method	When to use
Knowledge Graph Explorer ↗	For visually exploring certain Knowledge Graph use cases in the browser
Local files	For offline access and custom processing of Knowledge Graph data — download open datasets using `curl`, or download any dataset using the Dataset catalog ↗ Can be used across graph databases, relational systems, in-memory tools, and AI pipelines without requiring any specialized infrastructure
REST API	For real-time programmatic access to Knowledge Graph data in an application
MCP server	For using Knowledge Graph data natively with an LLM
Agent plugins	For asking ChatGPT or Claude about Knowledge Graph data

Steps

Local files
REST API
MCP server
Agent plugins

Query the Knowledge Graph for the educational data you’re interested in.

Use the Dataset catalog

Open the Dataset catalog

Sign in to Platform ↗ and open the Dataset catalog ↗.See Dataset catalog for how datasets are grouped and which files are , , , or .

Choose a dataset or file

Browse a category and open the dataset you need. Each dataset includes one or more file downloads.If you only need part of a dataset (e.g., ELA standards from U.S. academic standards), download that file — you do not need the whole dataset or the entire Knowledge Graph.

Download or request access

For Open files, download the listed JSONL files and query them locally.For Gated files, an organization Admin can request access from the publisher.

Download directly

Download the Knowledge Graph files

You can download all open datasets in the Knowledge Graph using the following methods:

Direct links - nodes.jsonl ↗ and relationships.jsonl ↗

curl ↗ commands:

# Entities
curl -L "https://cdn.learningcommons.org/knowledge-graph/v1.15.0/exports/nodes.jsonl?ref=docs_curl" -o nodes.jsonl

# Relationships
curl -L "https://cdn.learningcommons.org/knowledge-graph/v1.15.0/exports/relationships.jsonl?ref=docs_curl" -o relationships.jsonl

To download gated datasets, an organization Admin can request access in the Dataset catalog ↗.

Install jq

Install jq ↗, a lightweight command-line JSON processor.

Query the JSONL files

Query your downloaded files for the data you’re interested in.e.g., To get Common Core Math Standards, filter for nodes with a StandardsFrameworkItem label, a Multi-State jurisdiction (Common Core), and a Mathematics academic subject:

jq -c 'select((.labels | contains(["StandardsFrameworkItem"])) and .properties.jurisdiction == "Multi-State" and .properties.academicSubject == "Mathematics")' nodes.jsonl > common_core_math_standards.jsonl

Retrieve a list of standards for Multi-State Mathematics.

Generate your API key

Get a standards framework UUID

Send a request to the GET /standards-frameworks API endpoint to get the caseIdentifierUUID for Multi-State Mathematics.

curl -X GET \
  -H "x-api-key: YOUR_API_KEY" \
  "https://api.learningcommons.org/knowledge-graph/v0/standards-frameworks?academicSubject=Mathematics&jurisdiction=Multi-State"

import os
import requests

# Setup
api_key = os.getenv("API_KEY")  # Your API key from Platform
base_url = os.getenv("BASE_URL")  # Your base URL from Platform; follows https://api.learningcommons.org/knowledge-graph/v0 format

headers = { "x-api-key": api_key }

response = requests.get(
    f"{base_url}/standards-frameworks",
    headers=headers,
    params={
        "academicSubject": "Mathematics",
        "jurisdiction": "Multi-State"
    }
)

result = response.json()
print(result)

const apiKey = process.env.API_KEY; // Your API key from Platform
const baseUrl = process.env.BASE_URL; // Your base URL from Platform

const response = await fetch(
  `${baseUrl}/standards-frameworks?academicSubject=Mathematics&jurisdiction=Multi-State`,
  {
    method: 'GET',
    headers: { 'x-api-key': apiKey }
  }
);

const data = await response.json();
console.log(data);

Copy the caseIdentifierUUID from the response to use in the next step.

Retrieve Academic Standards

Use the caseIdentifierUUID with the GET /academic-standards API endpoint to retrieve the individual standards for that framework.

curl -X GET \
  -H "x-api-key: YOUR_API_KEY" \
  "https://api.learningcommons.org/knowledge-graph/v0/academic-standards?standardsFrameworkCaseIdentifierUUID=YOUR_UUID_FROM_STEP_1"

import os
import requests

# Setup
api_key = os.getenv("API_KEY")  # Your API key from Platform
base_url = os.getenv("BASE_URL")  # Your base URL from Platform
framework_uuid = "YOUR_UUID_FROM_STEP_1"  # Copy from Step 1 response

# Make request
headers = {
    "x-api-key": api_key
}

response = requests.get(
    f"{base_url}/academic-standards",
    headers=headers,
    params={
        "standardsFrameworkCaseIdentifierUUID": framework_uuid
    }
)

result = response.json()
print(result)

const apiKey = process.env.API_KEY; // Your API key from Platform
const baseUrl = process.env.BASE_URL; // Your base URL from Platform
const frameworkUuid = "YOUR_UUID_FROM_STEP_1"; // From Step 1 response

const response = await fetch(
  `${baseUrl}/academic-standards?standardsFrameworkCaseIdentifierUUID=${frameworkUuid}`,
  {
    method: 'GET',
    headers: {
      'x-api-key': apiKey
    }
  }
);

const data = await response.json();
console.log(data);

Response

{
  "data": [
    {
      "identifier": "e1755456-c533-5a84-891e-59725c0479e0",
      "caseIdentifierURI": "https://satchelcommons.com/ims/case/v1p0/CFItems/6b9bf846-d7cc-11e8-824f-0242ac160002",
      "caseIdentifierUUID": "6b9bf846-d7cc-11e8-824f-0242ac160002",
      "name": null,
      "statementCode": "3.NF.A.1",
      "description": "Understand a fraction $\\frac{1}{b}$ as the quantity formed by 1 part when a whole is partitioned into b equal parts; understand a fraction $\\frac{a}{b}$ as the quantity formed by a parts of size $\\frac{1}{b}$.",
      "statementType": "Standard",
      "normalizedStatementType": "Standard",
      "jurisdiction": "Multi-State",
      "academicSubject": "Mathematics",
      "gradeLevel": ["3"],
      "inLanguage": "en-US",
      "dateCreated": null,
      "dateModified": "2025-02-05",
      "notes": null,
      "author": "1EdTech",
      "provider": "Learning Commons",
      "license": "https://creativecommons.org/licenses/by/4.0/",
      "attributionStatement": "Knowledge Graph is provided by Learning Commons under the CC BY-4.0 license. Learning Commons received state standards and written permission under CC BY-4.0 from 1EdTech."
    }
  ],
  "pagination": {
    "limit": 1,
    "nextCursor": "eyJpZGVudGlmaWVyIjogImUxNzU1NDU2LWM1MzMtNWE4NC04OTFlLTU5NzI1YzA0NzllMCJ9",
    "hasMore": true
  }
}

Ask about standards, learning components, or learning progressions.

Generate your API key

Choose an AI client

Download an AI client that supports MCP (e.g., OpenAI with the Responses API).

Set up environment variables

.env

OPENAI_API_KEY=
MCP_AUTH_KEY=
MCP_SERVER_URL=https://kg.mcp.learningcommons.org/mcp

Connect to the MCP server

Make a request to the MCP server with your question – e.g., “What are the learning components for California standard 4.OA.A.3?”

import os
import requests
from dotenv import load_dotenv

load_dotenv()

response = requests.post(
    "https://api.openai.com/v1/responses",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.getenv('OPENAI_API_KEY')}",
    },
    json={
        "model": "gpt-4o",
        "tools": [
            {
                "type": "mcp",
                "server_label": "learning-commons-kg",
                "server_url": os.getenv("MCP_SERVER_URL"),
                "require_approval": "never",
                "headers": {"x-api-key": os.getenv("MCP_AUTH_KEY")},
            }
        ],
        "input": "What are the learning components for California standard 4.OA.A.3?",
    },
)

print(response.json())

import "dotenv/config";

const response = await fetch("https://api.openai.com/v1/responses", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    Authorization: `Bearer ${process.env.OPENAI_API_KEY}`,
  },
  body: JSON.stringify({
    model: "gpt-4o",
    tools: [
      {
        type: "mcp",
        server_label: "learning-commons-kg",
        server_url: process.env.MCP_SERVER_URL,
        require_approval: "never",
        headers: {"x-api-key": process.env.MCP_AUTH_KEY},
      },
    ],
    input: "What are the learning components for California standard 4.OA.A.3?",
  }),
});

console.log(await response.json());

If using an SDK, verify how to pass in the MCP authorization key for your client.

Review the response

Your AI client will call Knowledge Graph MCP tools to return structured results (e.g., standard statements, learning components, etc.).Inspect mcp_call output entries for tool names, arguments, and results.

ChatGPT plugin

Get authoritative standards data when asking about a standard code.

Add the Learning Commons plugin

Search for Learning Commons in the ChatGPT plugin library and add it to your account.The plugin is included in OpenAI’s K-12 Educator plugin experience for ChatGPT for Teachers ↗ (U.S. K-12) and ChatGPT Education. Individual ChatGPT users may also be able to add it depending on their plan and available plugin settings.

Ask about a standard

Ask ChatGPT questions about a standard.Mention the grade level, state, and/or standard code (e.g., 5.NBT.A.2 or RL.4.1) that you are interested in:

“I’m a teacher in Utah. Generate 3 project ideas that address standard 3.W.1.”
“I am a 4th-grade teacher in California. A student is struggling with 4.OA.A.3. Which prior standards should I focus on?”

ChatGPT will use Knowledge Graph tools to look up the official statement, break standards into learning components, and trace learning progressions.

Claude connector

Get authoritative standards data when asking about a standard code.

Enable the Claude connector

Set up the Knowledge Graph integration in Claude ↗ from the Claude connector directory.

Ask about a standard

Ask Claude questions about a standard.Mention the grade level, state, and/or standard code (e.g., 5.NBT.A.2 or RL.4.1) that you are interested in:

“I’m a teacher in Iowa. Generate three project ideas that address W.3.4.”
“I am a 4th-grade teacher in California. A student is struggling with 4.OA.A.3. Which prior standards should I focus on?”

Claude will use Knowledge Graph tools to look up the official statement, break standards into learning components, and trace learning progressions.

API Reference

Explore API endpoints to access Knowledge Graph data programmatically.

Tutorials

Follow a step-by-step tutorial to query frameworks and tag content.

Understanding Knowledge Graph

Getting Started

Using Knowledge Graph

Datasets

Schema Reference

Resources

Using Knowledge Graph

Steps

Use the Dataset catalog

Download directly

ChatGPT plugin

Claude connector

API Reference

Tutorials

​Using Knowledge Graph

​Steps

​Use the Dataset catalog

​Download directly

​ChatGPT plugin

​Claude connector

​Related topics

API Reference

Tutorials

Using Knowledge Graph

Steps

Use the Dataset catalog

Download directly

ChatGPT plugin

Claude connector

Related topics