Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/neo4j-labs/create-context-graph/llms.txt

Use this file to discover all available pages before exploring further.

Create Context Graph can pull data from seven SaaS services and map it into your Neo4j knowledge graph. Connectors run at scaffold time to populate initial data, and are also generated into your project so you can re-import at any time.

​
Available connectors

GitHub

Repositories, issues, pull requests, commits, users, and code reviews. Auth: personal access token.

Notion

Pages, databases, blocks, users, and comments. Auth: internal integration token.

Jira

Projects, issues, sprints, users, comments, and worklogs. Auth: API token + Atlassian email.

Slack

Channels, messages, threads, users, and reactions. Auth: bot OAuth token.

Gmail

Emails, threads, contacts, labels, and attachment metadata (last 30 days). Auth: Google Workspace CLI or OAuth 2.0.

Google Calendar

Events, attendees, calendars, and recurring series (last 90 days). Auth: Google Workspace CLI or OAuth 2.0.

Salesforce

Accounts, contacts, opportunities, leads, cases, and activities. Auth: username/password.

​
Selecting connectors

​
Interactive wizard

Run the CLI and select connectors at the data source step: 
uvx create-context-graph my-app
  1. Select “Connect to SaaS services” when prompted for your data source.
  2. Pick one or more connectors from the checklist.
  3. Enter the required credentials for each selected connector.
The scaffolded project will include connector configuration in .env and an import pipeline in backend/scripts/.

​
CLI flags

Pass one --connector flag per service to skip the wizard: 
uvx create-context-graph my-app \
  --domain software-engineering \
  --framework pydanticai \
  --connector github \
  --connector slack
You can combine --connector with any domain, framework, or Neo4j flags. Each connector will prompt for its credentials unless they are already set as environment variables.

​
Re-importing data

After scaffolding, the generated project includes Makefile targets for data import: 
# Import data from all configured connectors
make import

# Import data and seed the graph with demo scenarios
make import-and-seed
These targets read credentials from the .env file in the project root.

​
Connector setup

​
GitHub

1

Generate a personal access token

Go to Settings > Developer settings > Personal access tokens > Tokens (classic).Generate a token with read access to the repository you want to import (the repo scope covers public and private repos).
2

Run with --connector github

uvx create-context-graph my-app \
  --domain software-engineering \
  --framework pydanticai \
  --connector github \
  --demo-data
The wizard will prompt you for:
  • GitHub personal access token — your ghp_... token
  • Repository — in owner/repo format, e.g. neo4j-labs/create-context-graph

​
Notion

1

Create an internal integration

Go to notion.so/my-integrations and create an internal integration. Copy the Internal Integration Secret.
2

Share content with your integration

Open the pages or databases you want to import, click Share, and add your integration.
3

Set the environment variable

NOTION_TOKEN=secret_xxxxxxxxxxxxxxxxxxxx

​
Jira

1

Create an API token

Go to id.atlassian.com/manage-profile/security/api-tokens and create an API token.
2

Run with --connector jira

uvx create-context-graph my-app \
  --domain software-engineering \
  --framework pydanticai \
  --connector jira
The wizard will prompt you for:
  • Jira instance URL — e.g. https://your-org.atlassian.net
  • Jira email — your Atlassian account email
  • Jira API token — the token you created above
  • Jira project key — e.g. PROJ, ENG, BACKEND

​
Slack

1

Create a Slack app

Go to api.slack.com/apps and create a new app.
2

Add bot token scopes

Under OAuth & Permissions, add these bot token scopes: channels:history, channels:read, users:read.
3

Install and copy the token

Install the app to your workspace and copy the Bot User OAuth Token (xoxb-...).
4

Run with --connector slack

uvx create-context-graph my-app \
  --domain personal-knowledge \
  --framework pydanticai \
  --connector slack
The wizard will prompt you for:
  • Slack Bot OAuth token — your xoxb-... token
  • Channel names to import — comma-separated (e.g. general,engineering) or all for all public channels

​
Gmail and Google Calendar

Gmail and Google Calendar share the same Google Cloud project credentials. Configuring one makes the other available with no extra setup.
1

Set up a Google Cloud project

Create a project in Google Cloud Console. Enable the Gmail API and/or Google Calendar API under APIs & Services > Library.
2

Create OAuth 2.0 credentials

Under APIs & Services > Credentials, create an OAuth 2.0 Client ID of type Desktop app. Download the JSON credentials file.
3

Set the environment variable

GOOGLE_CREDENTIALS_FILE=/path/to/credentials.json
4

Google Workspace CLI (optional)

The connectors prefer the gws CLI if it is installed. The wizard checks for gws automatically and offers to install it (pip install gws). If you skip the install, provide the service account JSON key file instead.
Both Gmail and Google Calendar connectors prefer the Google Workspace CLI (gws) for OAuth flows. If gws is not found, the connectors fall back to Python OAuth 2.0 automatically.

​
Salesforce

1

Gather your credentials

You need your Salesforce username, password, and security token. To reset your security token, go to Settings > Personal > Reset My Security Token in Salesforce.
2

Run with --connector salesforce

uvx create-context-graph my-app \
  --domain financial-services \
  --framework pydanticai \
  --connector salesforce
The wizard will prompt you for:
  • Salesforce username — your login email
  • Salesforce password — your Salesforce password
  • Salesforce security token — from Settings > Personal > Reset My Security Token
  • Salesforce domain — login for production, test for sandbox

Build docs developers (and LLMs) love

Get started for freeTalk to us