Skip to main content

MCP server for the Airbyte Public API (self-managed / Cloud).

Project description

Airbyte MCP Server (airbyte-mcp)

MCP server for the Airbyte Public API. Built with the official MCP Python SDK (FastMCP).

Lets any MCP-compatible client (Cursor, Claude Desktop, Claude Code, MCP Inspector, etc.) interact with your Airbyte instance through natural language.

Features

  • 36 tools covering workspaces, sources, destinations, connections, jobs, refresh/clear, job logs, tags, streams, and connector definitions
  • Read and write operations for core resources (create, update, delete)
  • Job diagnostics via the internal Configuration API (self-managed): detailed failure reasons, per-stream stats, and structured logs
  • Cloud full-text sync logs via airbyte_get_cloud_sync_logs (Airbyte Cloud only; parity with official Replication MCP)
  • Automatic token exchange with in-memory caching and transparent 401 retry
  • Markdown and JSON response formats on summary tools; JSON-only for log tools
  • Pagination support (limit/offset) on all list tools
  • Runs over stdio (local) — works with Cursor, Claude Desktop, Claude Code, and Docker
  • Works with self-managed Airbyte (abctl) and Airbyte Cloud

Available Tools

Tool Description
Health
airbyte_health_check Ping the Airbyte API
Workspaces
airbyte_list_workspaces List workspaces with pagination
airbyte_get_workspace Get workspace details by ID
Sources
airbyte_list_sources List source connectors (filter by workspace)
airbyte_get_source Get source details by ID
airbyte_create_source Create a new source connector
airbyte_update_source Update an existing source
Destinations
airbyte_list_destinations List destination connectors (filter by workspace)
airbyte_get_destination Get destination details by ID
airbyte_create_destination Create a new destination connector
airbyte_update_destination Update an existing destination
Connections
airbyte_list_connections List connections / pipelines (filter by workspace)
airbyte_get_connection Get connection details including stream config
airbyte_create_connection Create a new connection (pipeline)
airbyte_update_connection Update an existing connection
Jobs
airbyte_list_jobs List jobs (filter by connection, type, status, dates)
airbyte_get_job Get job details (status, duration, bytes/rows synced)
airbyte_trigger_sync Trigger a sync or reset job
airbyte_cancel_job Cancel a running job
airbyte_trigger_refresh Trigger a per-stream refresh (internal API, self-managed)
airbyte_trigger_clear Clear destination data for streams (internal API, self-managed)
airbyte_wait_for_job Poll until a job reaches a terminal status (internal API)
Job Logs (Internal API — self-managed only)
airbyte_list_jobs_internal List all job types including refresh and clear
airbyte_get_job_details Per-attempt stats, failure reasons, and stacktraces
airbyte_get_job_logs Structured log entries for all attempts
airbyte_get_attempt_logs Structured log entries for a specific attempt
Job Logs (Cloud only — full text)
airbyte_get_cloud_sync_logs Full-text sync logs with pagination (Cloud Config API)
Streams
airbyte_get_stream_properties Get stream properties for a source/destination pair
Tags
airbyte_list_tags List tags
airbyte_create_tag Create a tag
airbyte_update_tag Update a tag
airbyte_delete_tag Delete a tag
Connector Definitions
airbyte_list_source_definitions List source connector definitions
airbyte_get_source_definition Get a source connector definition
airbyte_list_destination_definitions List destination connector definitions
airbyte_get_destination_definition Get a destination connector definition

See docs/endpoints.md for the full Airbyte API endpoint checklist.

Prerequisites

  • A running Airbyte instance — either:
  • One of the following to run the server:
    • uvx (zero-install; runs the published package on demand — see Run with uvx), or
    • uv + Python 3.13+ (local clone / development), or
    • Docker (no Python / uv needed on the host)

Quickstart

1. Clone and install

git clone https://github.com/trustxai/airbyte-mcp.git
cd airbyte-mcp
uv sync

2. Configure credentials

cp .env.example .env

For self-managed (abctl), retrieve credentials:

abctl local credentials

Edit .env with your client-id and client-secret. See docs/authentication.md for details.

3. Run the server

uv run airbyte-mcp

Run with uvx (zero-install)

uvx runs the published PyPI package on demand — no clone, no virtualenv, no persistent install. The command matches the package name, so no --from is needed:

uvx airbyte-mcp

Not the same as the official Airbyte replication MCP. That one lives in the airbyte package and is invoked as uvx --from=airbyte@latest airbyte-mcp. Here the PyPI package is airbyte-mcp, so uvx airbyte-mcp unambiguously resolves to this server.

Credentials are passed via the client's env block (see below), or exported in your shell for a manual run:

AIRBYTE_API_URL=http://localhost:8000/api/public/v1 \
AIRBYTE_CLIENT_ID=<your-client-id> \
AIRBYTE_CLIENT_SECRET=<your-client-secret> \
uvx airbyte-mcp

Python version: the package targets Python 3.13+. uv auto-provisions a matching interpreter, so this normally just works. If your environment pins an older default, force it with uvx --python=3.13 airbyte-mcp.

Client config (e.g. Cursor .cursor/mcp.json) using uvx:

{
  "mcpServers": {
    "airbyte": {
      "command": "uvx",
      "args": ["airbyte-mcp"],
      "env": {
        "AIRBYTE_API_URL": "http://localhost:8000/api/public/v1",
        "AIRBYTE_CLIENT_ID": "<your-client-id>",
        "AIRBYTE_CLIENT_SECRET": "<your-client-secret>"
      }
    }
  }
}

Client Configuration

Every MCP client (Cursor, Claude Desktop, etc.) can run the server in one of three ways:

  • uvx — zero-install; runs the published package on demand (see Run with uvx).
  • uv — from a local clone; best for development.
  • Docker — no Python / uv required on the host; everything runs in a container. Build the image once and every client config reuses it.

Host networking note: if Airbyte is running on your host machine (e.g. via abctl), inside the Docker container localhost does not point to your host. Use http://host.docker.internal:8000/api/public/v1 on macOS/Windows, or add --network=host to the docker run args on Linux.

Build the Docker image (one-time)

docker build -t airbyte-mcp:latest .

Cursor

Add to .cursor/mcp.json (project-level) or ~/.cursor/mcp.json (global):

Option A — uv

{
  "mcpServers": {
    "airbyte": {
      "command": "uv",
      "args": ["--directory", "/path/to/airbyte-mcp", "run", "airbyte-mcp"],
      "env": {
        "AIRBYTE_API_URL": "http://localhost:8000/api/public/v1",
        "AIRBYTE_CLIENT_ID": "<your-client-id>",
        "AIRBYTE_CLIENT_SECRET": "<your-client-secret>"
      }
    }
  }
}

Option B — Docker

{
  "mcpServers": {
    "airbyte": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "--name", "airbyte-mcp",
        "-e", "AIRBYTE_API_URL",
        "-e", "AIRBYTE_CLIENT_ID",
        "-e", "AIRBYTE_CLIENT_SECRET",
        "airbyte-mcp:latest"
      ],
      "env": {
        "AIRBYTE_API_URL": "http://host.docker.internal:8000/api/public/v1",
        "AIRBYTE_CLIENT_ID": "<your-client-id>",
        "AIRBYTE_CLIENT_SECRET": "<your-client-secret>"
      }
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

Option A — uv

{
  "mcpServers": {
    "airbyte": {
      "command": "uv",
      "args": ["--directory", "/path/to/airbyte-mcp", "run", "airbyte-mcp"],
      "env": {
        "AIRBYTE_API_URL": "http://localhost:8000/api/public/v1",
        "AIRBYTE_CLIENT_ID": "<your-client-id>",
        "AIRBYTE_CLIENT_SECRET": "<your-client-secret>"
      }
    }
  }
}

Option B — Docker

{
  "mcpServers": {
    "airbyte": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "--name", "airbyte-mcp",
        "-e", "AIRBYTE_API_URL",
        "-e", "AIRBYTE_CLIENT_ID",
        "-e", "AIRBYTE_CLIENT_SECRET",
        "airbyte-mcp:latest"
      ],
      "env": {
        "AIRBYTE_API_URL": "http://host.docker.internal:8000/api/public/v1",
        "AIRBYTE_CLIENT_ID": "<your-client-id>",
        "AIRBYTE_CLIENT_SECRET": "<your-client-secret>"
      }
    }
  }
}

Claude Code

claude mcp add \
  --env AIRBYTE_API_URL=http://localhost:8000/api/public/v1 \
  --env AIRBYTE_CLIENT_ID=<your-client-id> \
  --env AIRBYTE_CLIENT_SECRET=<your-client-secret> \
  --transport stdio \
  airbyte \
  -- uvx airbyte-mcp

MCP Inspector

The Inspector can launch the stdio server directly:

npx @modelcontextprotocol/inspector uvx airbyte-mcp

Set AIRBYTE_API_URL, AIRBYTE_CLIENT_ID, and AIRBYTE_CLIENT_SECRET in the Inspector's environment panel (or export them in your shell first).

Running Manually (without a client)

If you just want to exercise the server from the CLI:

# uvx — no clone
uvx airbyte-mcp

# uv
uv run airbyte-mcp

# Docker
docker run --rm -i --env-file .env airbyte-mcp:latest

Environment Variables

Variable Required Default Description
AIRBYTE_API_URL No http://localhost:8000/api/public/v1 Airbyte API base URL
AIRBYTE_CLIENT_ID Yes* Application client ID
AIRBYTE_CLIENT_SECRET Yes* Application client secret
AIRBYTE_ACCESS_TOKEN No Pre-fetched token (skips exchange)
AIRBYTE_INTERNAL_API_URL No (derived) Override Config API base (Cloud: https://cloud.airbyte.com/api/v1)
AIRBYTE_REQUEST_TIMEOUT_SECONDS No 30 Default HTTP timeout for public API calls
AIRBYTE_INTERNAL_LOG_TIMEOUT_SECONDS No 120 Timeout for internal/Cloud Config API log endpoints

*Not required if AIRBYTE_ACCESS_TOKEN is provided.

Documentation

Contributing

Contributions are welcome! See docs/CONTRIBUTING.md to get started.

License

Apache-2.0 — see LICENSE for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

airbyte_mcp-1.0.0.tar.gz (97.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

airbyte_mcp-1.0.0-py3-none-any.whl (51.0 kB view details)

Uploaded Python 3

File details

Details for the file airbyte_mcp-1.0.0.tar.gz.

File metadata

  • Download URL: airbyte_mcp-1.0.0.tar.gz
  • Upload date:
  • Size: 97.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.26 {"installer":{"name":"uv","version":"0.11.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for airbyte_mcp-1.0.0.tar.gz
Algorithm Hash digest
SHA256 4ce0bb106b5ea0c2af9f21ed356945ed3684e3a302b957813a46e80b67c65d16
MD5 d70001382cbf7287401cb87691b70095
BLAKE2b-256 0ab2ce3955c68b783f1b2a86f453fa4b37fc8a10bfea1abb46f6382b326ff332

See more details on using hashes here.

File details

Details for the file airbyte_mcp-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: airbyte_mcp-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 51.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.26 {"installer":{"name":"uv","version":"0.11.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for airbyte_mcp-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 487d63354392406ecbedaeed8ef3303a20e57cff8accb9f190b3e811d2aa1c0b
MD5 33c2e1898f11e3de7b09fab3c0b7341b
BLAKE2b-256 0f0a230d78a1e3b7154aac67be87e34b804f89a16bd4e747541a9173e22b76eb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page