Skip to main content

MCP server that exposes Airbyte Connector SDK as MCP tools

Project description

Airbyte Agent MCP Server

MCP server that exposes the Airbyte Connector SDK as Model Context Protocol tools.

Features

  • Execute: Run operations on any connector (primary tool)
  • List Entities: Discover available entities in a connector
  • Describe Entity: Get detailed schema for an entity
  • Validate Operation: Check parameters before execution

Configuration

1. Create configured_connectors.yaml

# Connector definitions
connectors:
  # Load connector from the Airbyte registry (recommended)
  - id: stripe
    type: local
    connector_name: stripe
    description: "My Stripe API connector"
    secrets:
      token: STRIPE_API_KEY

You can pin to a specific version from the registry:

connectors:
  - id: stripe
    type: local
    connector_name: stripe
    version: 0.1.0
    description: "Stripe connector pinned to v0.1.0"
    secrets:
      token: STRIPE_API_KEY

You can also load connectors from a local file path (version pinning not supported):

connectors:
  - id: my_api
    type: local
    path: ./connectors/my-api/connector.yaml
    description: "My custom API connector"
    secrets:
      token: MY_API_KEY

See configured_connectors.yaml.example for more examples.

2. Create .env file

STRIPE_API_KEY=sk_test_your_stripe_api_key_here

Running

uv run airbyte_agent_mcp

The server also takes in args for specific paths to the configured_connectors.yaml file and the env file. With custom paths:

python -m airbyte_agent_mcp path/to/configured_connectors.yaml path/to/.env

The default paths are ./configured_connectors.yaml and ./.env

Usage with Claude Code

Add to ~/.claude.json:

"mcpServers": {
  "airbyte-agent-mcp": {
    "type": "stdio",
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/sonar/airbyte-agent-mcp",
      "run",
      "airbyte_agent_mcp"
    ],
    "env": {}
  }
},

Development / Testing

# Install dev dependencies
uv sync --all-extras

# Run tests
uv run pytest

# Format code
uv run ruff format .

# Lint code
uv run ruff check .

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distribution

airbyte_agent_mcp-0.1.9.tar.gz (83.3 kB view details)

Uploaded Source

Built Distribution

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

airbyte_agent_mcp-0.1.9-py3-none-any.whl (102.8 kB view details)

Uploaded Python 3

File details

Details for the file airbyte_agent_mcp-0.1.9.tar.gz.

File metadata

  • Download URL: airbyte_agent_mcp-0.1.9.tar.gz
  • Upload date:
  • Size: 83.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.11

File hashes

Hashes for airbyte_agent_mcp-0.1.9.tar.gz
Algorithm Hash digest
SHA256 447911cdb7e24c15f55eca6f8de1d4cd46a60fc8726049bc33f2a4e2be1a6d34
MD5 f21d08bf510aef793f3ee12168e25b30
BLAKE2b-256 bc7d497338501daf4582b4b19add63b8205a647be9b2473e321bb4d6ffc9aa47

See more details on using hashes here.

File details

Details for the file airbyte_agent_mcp-0.1.9-py3-none-any.whl.

File metadata

File hashes

Hashes for airbyte_agent_mcp-0.1.9-py3-none-any.whl
Algorithm Hash digest
SHA256 ba97dbd59da422220c19b0c2119dfa9b152477fe6b32ac35e158e52b40934772
MD5 f66aa65be3f43f888f31a8d03691d6c1
BLAKE2b-256 13bc3ad0a2977a87ff2a8885f32dc812274fd470ea4e90c0c4901e08b92ffd1c

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