---
id: airbyte-internal-ops
version: "0.100.0"
license: unclear
license_treatment: permissive
maintenance: active
---

# airbyte-internal-ops — MCP and API interfaces that let the agents do the admin work

License: permissive · Maintenance: active · Downloads: 131.2K/mo

## What it is and what it does

airbyte-internal-ops is an MCP server and command-line tool that exposes Airbyte administrative operations to agents and clients. It bridges agent interfaces (like Claude or Goose) with Airbyte's internal APIs, allowing automated management of connectors, workspaces, and infrastructure. The package includes both a local stdio-based MCP server and HTTP endpoints for hosted deployments, with support for OAuth and bearer-token authentication.

The package is built on top of airbyte-cdk and airbyte-protocol-models, integrating with Google Cloud services (logging, secrets, storage), Docker, Git, and a large ecosystem of async and CLI frameworks. It is designed for operators and agents performing administrative tasks like connector registry management, progressive rollout automation, and workspace administration. Configuration is environment-driven via .env files, and the package includes comprehensive CLI documentation and agent-specific guidance.

Use it for:

- Automate Airbyte connector registry operations and release-block management through agent-driven CLI commands.
- Integrate Airbyte admin workflows into AI agent systems via MCP protocol for hands-off infrastructure management.
- Manage Airbyte Cloud workspaces and credentials programmatically using the HTTP MCP endpoint with OAuth or bearer tokens.
- Run progressive rollout automation for connector updates with operator-facing controls and monitoring.
- Query and manage Airbyte internal state (secrets, logging, storage) via unified admin API interfaces.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Provides MCP (Model Context Protocol) server and CLI tools for Airbyte administrative operations, enabling agents and clients to manage Airbyte infrastructure programmatically.

Yes, if you are an Airbyte operator or developer building agent-driven automation for Airbyte infrastructure. The package is actively maintained, has no known vulnerabilities, and provides low install friction. However, it is in Beta (0.x) and appears designed primarily for Airbyte's internal use; verify that it supports your deployment model (cloud vs. self-hosted) and that your authentication method (OAuth, bearer token, or stdio) is available before committing to it.

## Install

pip install airbyte-internal-ops
uv add airbyte-internal-ops
poetry add airbyte-internal-ops

## Installing airbyte-internal-ops

Before you install: Low install friction with a pure-Python wheel distribution. Active maintenance as of the latest release. Requires Python 3.11 or 3.12; capped below current Python versions. Brings in 41 runtime dependencies including airbyte-cdk, cloud connectors, and MCP frameworks.

License in practice: Licensed under MIT (permissive), allowing unrestricted use, modification, and distribution with minimal legal constraints.

Quickstart:

# Install the package
pip install airbyte-internal-ops

# Set up environment credentials
export AIRBYTE_CLOUD_CLIENT_ID="..."
export AIRBYTE_CLOUD_CLIENT_SECRET="..."
export AIRBYTE_MCP_ENV_FILE="~/.mcp/airbyte_mcp.env"

# Run the MCP server via stdio
airbyte-ops-mcp

# Or import and use the CLI directly
from airbyte_internal_ops import cli
cli.main()

Requires Python 3.11 or 3.12 (capped below 3.13). Airbyte Cloud credentials (client ID and secret) and optional admin flag environment variables must be configured for full functionality.

Verify before relying:

- Whether the package is intended for internal Airbyte use only or is suitable for external operators managing Airbyte deployments.
- Stability guarantees or breaking-change policy given the 0.x version number and Beta development status.
- Performance characteristics and resource requirements when running the MCP server under load.

## Package facts

- License: not declared (permissive)
- Python support: capped_below_current
- Install friction: low
- Maintenance: active
- Downloads: 131.2K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

airbyte admin automation, mcp server airbyte, airbyte operations cli, airbyte agent tools, airbyte infrastructure management, model context protocol airbyte, airbyte connector registry, airbyte cloud operations, mcp-server, airbyte-ops, agent-automation

[View on SkillFed](https://skillfed.io/packages/airbyte-internal-ops) · [View on PyPI](https://pypi.org/project/airbyte-internal-ops/)