Skip to content
J·BJon BishopFractional growth marketer

Data platforms · llms.txt file breakdown

Mage AI llms.txt

A directly retrieved Markdown index for Mage AI's documentation, with 468 links across 2 detected headings.

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Open saved text ↗

Showing the first 18000 characters. Load the complete file to read the remainder.

# Mage AI

## Docs

- [Mage Pro](https://docs.mage.ai/production/mage/pro.md): A powerful, cloud-native solution to orchestrate and scale your data pipelines — available as fully managed, private, or hybrid cloud deployments.
- [Deployment architecture overview](https://docs.mage.ai/pro-architecture/architecture-overview.md): Deploy Mage Pro in any environment
- [Managed cloud](https://docs.mage.ai/pro-architecture/saas.md): Fully managed Mage Pro
- [Hybrid cloud deployment](https://docs.mage.ai/pro-architecture/hybrid-cloud.md): Deploy the data plane in your cloud environment
- [Private cloud deployment](https://docs.mage.ai/pro-architecture/private-cloud.md): Deploy securely in your private cloud environment
- [On-prem deployment](https://docs.mage.ai/pro-architecture/on-prem.md): Deploy securely from your own on-prem servers
- [Cluster Management](https://docs.mage.ai/getting-started/cluster-management-portal.md): Manage all your Mage Pro clusters
- [Mage Pro API](https://docs.mage.ai/getting-started/mage-pro-api.md): Deploy your code in seconds!
- [Install dependencies](https://docs.mage.ai/getting-started/install-dependencies.md): Install dependencies using requirements.txt with automatic environment management
- [Mage Pro workspaces](https://docs.mage.ai/guides/developer-ux/workspaces.md): Set up Mage Pro workspaces for organizing your own personal environment.
- [Mage Pro data pipeline](https://docs.mage.ai/getting-started/build-pro-pipeline.md): Build your first Mage Pro data pipeline
- [Mage Pro pipeline trigger](https://docs.mage.ai/getting-started/trigger-pipeline.md): Trigger your first Mage Pro data pipeline
- [Best Practices](https://docs.mage.ai/guides/best-practices.md): Learn best practices for building, maintaining, and scaling data pipelines in Mage Pro.
- [Introduction](https://docs.mage.ai/agent/introduction.md): Build and manage Mage data pipelines directly from your AI coding assistant.
- [Quickstart](https://docs.mage.ai/agent/quickstart.md): Install mage-agent, log in, and make your first AI-assisted pipeline call in under five minutes.
- [Installation](https://docs.mage.ai/agent/installation.md): System requirements and install options for mage-agent.
- [Mage Agent Plugin](https://docs.mage.ai/agent/mage-agent-plugin.md): Install the Mage Agent Plugin and connect it to a Mage cluster.
- [Authentication](https://docs.mage.ai/agent/authentication.md): Log in to your Mage Pro cluster and manage credentials.
- [IDE Integration](https://docs.mage.ai/agent/ide-integration.md): Connect Cursor, Claude Code, OpenAI Codex CLI, or another MCP-compatible AI client to your Mage Pro cluster via MCP.
- [Syncing Local Files](https://docs.mage.ai/agent/sync.md): Mirror your Mage Pro project to a local directory and push edits back to the cluster.
- [MCP Tools](https://docs.mage.ai/agent/mcp-tools.md): Full reference for every tool your AI assistant can call via mage-agent.
- [CLI Reference](https://docs.mage.ai/agent/cli-reference.md): All mage-agent commands and their options.
- [Troubleshooting](https://docs.mage.ai/agent/troubleshooting.md): Solutions for common mage-agent issues.
- [Mage Pro CI/CD overview](https://docs.mage.ai/development/git/pro-overview.md): Deploy your code in seconds!
- [Mage Pro CI/CD workflow](https://docs.mage.ai/guides/data-sync/cicd-workflow.md): Deploy and manage your pipeline code safely across environments using Mage Pro's integrated deployment application.
- [Git terminal with built-in authentication and shortcuts](https://docs.mage.ai/guides/data-sync/git-terminal.md): Mage Pro supports Git-based version control, making it easy to  collaborate, track changes, and manage code across environments.
- [File versioning and history](https://docs.mage.ai/guides/version-control/file-versions.md): Local file edit tracking and version history for restoring changes made in the past.
- [Mage Pro Version Control](https://docs.mage.ai/guides/data-sync/version-control-guide.md): Connect your data pipelines to Git repositories and deploy code seamlessly. Authenticate with GitHub, BitBucket, or GitLab, manage code with Git commands, and deploy from commits to your Mage Pro cluster.
- [Using GitClient in Mage blocks](https://docs.mage.ai/guides/data-sync/git-client.md): Programmatically perform Git operations (add, commit, push, pull) directly within your Mage pipeline blocks using the GitClient class.
- [AI Blocks](https://docs.mage.ai/ai/blocks.md): Use AI blocks to turn prompts, upstream data, and pipeline context into reusable pipeline outputs.
- [Retrieval Augmented Generation (RAG) pipeline builder](https://docs.mage.ai/ai/rag-pipeline.md): Build and deploy RAG pipelines with ease.
- [Customized AI resources for training and inference](https://docs.mage.ai/ai/custom-resources.md)
- [Level 99 dynamic abilities](https://docs.mage.ai/guides/blocks/dynamic-blocks-2.md): Execute 100,000+ dynamically created block runs concurrently with upgraded memory management and concurrency.
- [Level 99 dynamic abilities](https://docs.mage.ai/guides/blocks/batch-read-write.md): Granular block settings for controlling read/write data partitions using output size, number of chunks, and item count.
- [OracleDB](https://docs.mage.ai/guides/streaming/sources/oracledb.md): Stream changes from OracleDB with OracleDB CDC.
- [Stateful Streaming Pipeline](https://docs.mage.ai/guides/streaming/tutorials/streaming-stateful-store.md): Create and use stateful store in a streaming pipeline.
- [Custom source](https://docs.mage.ai/data-integrations/sources/custom_source.md): Easily plug in your own data integration sources and destinations with Mage Pro.
- [Adapt an existing source](https://docs.mage.ai/contributing/data-integrations/adapt-existing-source.md): Mage builds data integrations from [Singer taps](https://www.singer.io/#taps), so if there's a Singer source you want to use that isn't supported yet, you can adapt it yourself!
- [Create a new source](https://docs.mage.ai/contributing/data-integrations/add-new-source.md): This guide details adding a new source to Mage. If your source already exists as a [Singer tap](https://www.singer.io/#taps), check out [our guide](/contributing/data-integrations/adapt-existing-source) for adapting an existing source instead.
- [Create a new destination](https://docs.mage.ai/contributing/data-integrations/add-new-destination.md)
- [Facebook Pages](https://docs.mage.ai/data-integrations/sources/facebook_pages.md)
- [Instagram](https://docs.mage.ai/data-integrations/sources/instagram.md)
- [QuickBooks](https://docs.mage.ai/data-integrations/sources/quickbooks.md)
- [Xero](https://docs.mage.ai/data-integrations/sources/xero.md): Sync accounting data from Xero including invoices, contacts, payments, and more. Supports incremental syncing with automatic OAuth token refresh.
- [YouTube Analytics API Source](https://docs.mage.ai/data-integrations/sources/youtube_analytics.md): This guide explains how to configure the YouTube Analytics API as a data source in Mage. Learn how to authenticate with Google Cloud, request the necessary OAuth scopes, and sync data from specific channels.
- [Google Campaign Manager 360](https://docs.mage.ai/data-integrations/sources/google_campaign_manager_360.md): Sync entity data and Report Builder exports from Campaign Manager 360 using the DFA Reporting & Trafficking API v5 and a service account.
- [Google Display & Video 360](https://docs.mage.ai/data-integrations/sources/google_display_video_360.md): Sync DV360 entity metadata and Bid Manager performance report data from Google's Display & Video 360 platform using a service account.
- [Microsoft Ads](https://docs.mage.ai/data-integrations/sources/microsoft_ads.md): Sync performance reports from the Microsoft Advertising API (Bing Ads v13) using OAuth 2.0 and the official bingads Python SDK.
- [Salesforce Marketing Cloud](https://docs.mage.ai/data-integrations/sources/salesforce_marketing_cloud.md): Sync campaigns, journeys, assets, subscribers, and engagement events from Salesforce Marketing Cloud using the REST and SOAP APIs.
- [TikTok Ads](https://docs.mage.ai/data-integrations/sources/tiktok_ads.md): Sync ad management objects and performance insight reports from the TikTok Marketing API using a long-lived access token.
- [Databricks](https://docs.mage.ai/data-integrations/destinations/databricks.md): How to configure Databricks as a destination in Mage to write pipeline data to Databricks SQL warehouses using Unity Catalog.
- [DuckDB](https://docs.mage.ai/data-integrations/destinations/duckdb.md): How to configure DuckDB as a destination in Mage to write pipeline data to local DuckDB files for fast, embedded analytics.
- [Iceberg S3](https://docs.mage.ai/data-integrations/destinations/iceberg_s3.md): How to configure Apache Iceberg on S3 as a destination in Mage to write data to ACID-compliant Iceberg tables stored in AWS S3.
- [Cross-pipeline dependencies](https://docs.mage.ai/guides/developer-ux/pipeline-dependencies.md): Manage cross-pipeline dependencies and execution flow across every pipeline within a project.
- [Pipeline editor canvas](https://docs.mage.ai/guides/developer-ux/code-canvas.md): Build, run, and manage complex pipelines with the new canvas mode.
- [Code editor with enhanced productivity](https://docs.mage.ai/guides/developer-ux/code-browser.md): Code browser and editor with syntax highlighting, code formatting, and version history.
- [Personalize your workspace](https://docs.mage.ai/guides/developer-ux/personalize.md): Customize workspace themes, personalize accounts, and re-configure UI component layouts.
- [Develop Mage Pro Code with VS Code or Cursor](https://docs.mage.ai/guides/developer-ux/visual-studio-code.md): Learn how to develop Mage Pro pipelines and projects using Visual Studio Code or Cursor. This guide walks you through secure remote access via Tailscale and SSH, environment configuration, and integrating your local IDE with Mage Pro.
- [PySpark in Mage Pro](https://docs.mage.ai/integrations/compute/spark-pro.md): This guide explains how to use PySpark in Mage Pro, including how to run PySpark blocks in batch pipelines, connect to Spark on Kubernetes, manage dependencies like Apache Iceberg, and access cloud storage securely. blocks in batch pipelines, manage dependencies like Apache Iceberg, and access cloud…
- [Compute management for Spark](https://docs.mage.ai/integrations/compute/management.md): Manage your Spark compute resources and track Spark pipeline execution metrics.
- [Databricks](https://docs.mage.ai/integrations/compute/databricks.md): This is a guide for using Databricks Spark cluster with Mage.
- [Databricks](https://docs.mage.ai/integrations/databases/Databricks.md)
- [Iceberg](https://docs.mage.ai/integrations/databases/Iceberg.md): Connect to Apache Iceberg tables stored in Amazon S3 using various catalog types
- [Migrate from Airbyte to Mage Pro](https://docs.mage.ai/migrations/airbyte-to-mage-pro.md)
- [Migrate from Airflow to Mage Pro](https://docs.mage.ai/migrations/airflow-to-mage-pro.md)
- [Migrate from dbt to Mage Pro](https://docs.mage.ai/migrations/dbt-to-mage-pro.md)
- [Migrate from Estuary to Mage Pro](https://docs.mage.ai/migrations/estuary-to-mage-pro.md)
- [Migrate from Fivetran to Mage Pro](https://docs.mage.ai/migrations/fivetran-to-mage-pro.md)
- [Migrate from Dagster to Mage Pro](https://docs.mage.ai/migrations/dagster-to-mage-pro.md)
- [Migrate from Mage OSS to Mage Pro](https://docs.mage.ai/migrations/mage-oss-to-mage-pro.md)
- [Migrate from Prefect to Mage Pro](https://docs.mage.ai/migrations/prefect-to-mage-pro.md)
- [Global Hooks](https://docs.mage.ai/extensibility/global-hooks/overview.md): Global Hooks are a powerful feature in Mage that allows you to execute custom functions before or after an API request. These hooks can be used to perform additional operations, validate data, or integrate with external systems.
- [Global Hooks Guide](https://docs.mage.ai/extensibility/global-hooks/guides.md): Follow this step by step guide on creating a global hook in Mage.
- [Mage Pro API overview](https://docs.mage.ai/extensibility/pro-api-reference/overview.md)
- [Create Deployment](https://docs.mage.ai/extensibility/pro-api-reference/deployments/overview.md)
- [Update Workspace](https://docs.mage.ai/extensibility/pro-api-reference/workspaces/update-workspace.md)
- [It’s magic.](https://docs.mage.ai/introduction/overview.md): Give your data team magical powers.
- [Quickstart](https://docs.mage.ai/getting-started/setup.md): Go from zero to Mage hero in under a minute. We'll walk you through installing Mage and running your first pipeline. 🦸‍♀️
- [Core Design Principles](https://docs.mage.ai/design/core-design-principles.md): Every user experience and technical design decision adheres to these principles.
- [Abstractions](https://docs.mage.ai/design/core-abstractions.md): These are the fundamental concepts that Mage uses to operate.
- [Project Structure](https://docs.mage.ai/design/abstractions/project-structure.md): Details about how the Mage file directory works and how typical projects are structured.
- [Pipeline Management](https://docs.mage.ai/design/data-pipeline-management.md)
- [Overview](https://docs.mage.ai/design/blocks.md): Each block in a pipeline maps to an individual file within a project. Blocks can be reused and shared across multiple pipelines within the same project.
- [Callback blocks](https://docs.mage.ai/design/blocks/callbacks.md): A callback block is associated to another block. When the parent block succeeds or fails, the callback block functions are executed.
- [Conditional blocks](https://docs.mage.ai/design/blocks/conditionals.md): A conditional block is an 'Add-on Block' associated with another block. The condition will be evaluated before the parent block is executed, determining if the parent block gets executed.
- [Data exporter](https://docs.mage.ai/design/blocks/data-exporter.md): After completing data transformations, utilize the data exporter blocks to either load the processed  data or store a machine learning model in an external data storage system.
- [Data loader](https://docs.mage.ai/design/blocks/data-loader.md): Write your code for fetching data from a remote source or loading it from disk.
- [Scratchpad](https://docs.mage.ai/design/blocks/scratchpad.md): Use these blocks to experiment and write throw away code.
- [Sensor](https://docs.mage.ai/design/blocks/sensor.md): A sensor is a block that continuously evaluates a condition until it’s met or until a period of time has elapsed.
- [Transformer](https://docs.mage.ai/design/blocks/transformer.md): Use these blocks to clean, transform, and enhance data from other blocks.
- [Dynamic blocks](https://docs.mage.ai/design/blocks/dynamic-blocks.md): Use the output of a block to dynamically create more blocks.
- [Data loader utilities](https://docs.mage.ai/design/data-loading.md)
- [Data loader templates](https://docs.mage.ai/development/blocks/data_loaders/templates.md)
- [Transformer templates](https://docs.mage.ai/development/blocks/transformers/templates.md)
- [Data exporter templates](https://docs.mage.ai/development/blocks/data_exporters/templates.md)
- [Sensor templates](https://docs.mage.ai/development/blocks/sensors/templates.md)
- [Callback templates](https://docs.mage.ai/development/blocks/callbacks/templates.md)
- [Conditional templates](https://docs.mage.ai/development/blocks/conditionals/templates.md)
- [Overview](https://docs.mage.ai/data-integrations/overview.md): Data integration is the process of synchronizing data between two systems.
- [Configure data integration pipelines](https://docs.mage.ai/data-integrations/configuration.md): There are many ways to configure your data integration pipeline.
- [Sources technical documentation](https://docs.mage.ai/data-integrations/sources/overview.md): A source is a system that you want to load data from and synchronize it into another system. A source can be a 3rd party API, SaaS, database, data warehouse, or a data lake.
- [Airtable](https://docs.mage.ai/data-integrations/sources/airtable.md)
- [Amazon S3](https://docs.mage.ai/data-integrations/sources/amazon_s3.md)
- [Amplitude](https://docs.mage.ai/data-integrations/sources/amplitude.md)
- [API Source Configuration](https://docs.mage.ai/data-integrations/sources/api.md): Learn how to configure API sources in Mage to extract data from RESTful and file-based endpoints. This guide covers authentication, pagination, response parsing, and advanced options available in Mage Pro.
- [Azure Blob Storage](https://docs.mage.ai/data-integrations/sources/azure_blob_storage.md)
- [BigQuery](https://docs.mage.ai/data-integrations/sources/bigquery.md)
- [Chargebee](https://docs.mage.ai/data-integrations/sources/chargebee.md)
- [Commercetools](https://docs.mage.ai/data-integrations/sources/commercetools.md)
- [Couchbase](https://docs.mage.ai/data-integrations/sources/couchbase.md)
- [Datadog](https://docs.mage.ai/data-integrations/sources/datadog.md)
- [Doris](https://docs.mage.ai/data-integrations/sources/doris.md)
- [Dremio](https://docs.mage.ai/data-integrations/sources/dremio.md)
- [Amazon DynamoDB](https://docs.mage.ai/data-integrations/sources/dynamodb.md): Use Mage to extract data from Amazon DynamoDB tables using AWS credentials or IAM roles.
- [Facebook Ads](https://docs.mage.ai/data-integrations/sources/facebook_ads.md)
- [Freshdesk](https://docs.mage.ai/data-integrations/sources/freshdesk.md)
- [Front](https://docs.mage.ai/data-integrations/sources/front.md)
- [GitHub](https://docs.mage.ai/data-integrations/sources/github.md)
- [Google Ads](https://docs.mage.ai/data-integrations/sources/google_ads.md): Sync campaign, ad group, keyword, and performance report data from the Google Ads API v23 using OAuth 2.0 authentication.
- [Google Analytics](https://docs.mage.ai/data-integrations/sources/google_analytics.md)
- [Google Cloud Storage](https://docs.mage.ai/data-integrations/sources/

Measured from the saved file

Linked document

UTF-8 text size
62.1 KB63605 bytes
Token count
15210o200k_base encoding
Markdown links
468467 distinct URLs
Fenced code blocks
0470 lines in the file

Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.

Project H1
Mage AI

Context architecture

How the content is divided

1 H2 sections organize 468 parsed Markdown links. 463 links point to .md or .markdown paths; 4 link occurrences use another hostname. Linked destinations have not been recursively validated.

H2 sectionLinksUTF-8 bytesTokens
DocsLine 34686358615204

Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.

Embedded material

Code, installation and API examples

Fenced blocks
0 closed
Declared languages
No fenced blocks detected
Package-install commands
0 detected in fenced or inline code
Authentication examples
0 fenced lines match API-key, Authorization, Bearer, OAuth or access-token patterns
HTTP request examples
0 fenced lines match request-method patterns
Authentication links
1 links have authentication-related labels

Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.

Publisher prioritization

The Optional section

No H2 section named “Optional” was detected in this file.

The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.

Machine-readable routes

MCP references and configuration text

MCP-related text was detected in the captured file. 1 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.

These are text and link observations. No MCP server connection, authentication or tool call was tested.

Index and bundle

llms-full.txt companion

Verified text companion

Text companion verified

https://docs.mage.ai/llms-full.txt ↗
Discovery
Conventional sibling path checked
HTTP response
200 · text/plain; charset=utf-8
Text size
Whole-file size not established by the bounded response
Token count
Not measured for the whole file
Retrieval scope
Bounded prefix inspected; the whole body was not downloaded

A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.

Change evidence

What can be said about freshness

This capture establishes a baseline. Update frequency cannot be determined from one observation.

Linked release and migration material

10 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.

File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.

Capture identity and measurement method
Requested endpoint
https://docs.mage.ai/llms.txt
Final endpoint
https://docs.mage.ai/llms.txt
HTTP status
200
Content type
text/plain; charset=utf-8
Text retrieval
Firecrawl literal text capture
Tokenizer
tiktoken 0.14.0 · o200k_base
SHA-256 of saved UTF-8 text
2ca7b511c612bbbd0aa53396aa597e99544f72dd2836f4f7bc14adfecd701d0c

Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.

Related tools and resources

Contact Jon