Gitlab
The Gitlab agent connector is a Python package that equips AI agents to interact with Gitlab through strongly typed, well-documented tools. It's ready to use directly in your Python app, in an agent framework, or exposed through an MCP.
Connector for the GitLab REST API (v4). Provides access to projects, issues, merge requests, commits, pipelines, groups, branches, releases, tags, members, milestones, and users. Supports both Personal Access Token and OAuth2 authentication.
Example prompts
The Gitlab connector is optimized to handle prompts like these.
- List all projects I have access to
- Get the details of a specific project
- List all open issues in a project
- Show merge requests for a project
- List all groups I belong to
- Show recent commits in a project
- List pipelines for a project
- Show all branches in a project
- Find issues updated in the last week
- What are the most active projects?
- Show merge requests that are still open
- List projects with the most commits
Unsupported prompts
The Gitlab connector isn't currently able to handle prompts like these.
- Create a new project
- Delete an issue
- Merge a merge request
- Trigger a pipeline
Entities and actions
This connector supports the following entities and actions. For more details, see this connector's full reference documentation.
| Entity | Actions |
|---|---|
| Projects | List, Get, Context Store Search |
| Issues | List, Get, Context Store Search |
| Merge Requests | List, Get, Context Store Search |
| Users | List, Get, Context Store Search |
| Commits | List, Get, Context Store Search |
| Groups | List, Get, Context Store Search |
| Branches | List, Get, Context Store Search |
| Pipelines | List, Get, Context Store Search |
| Group Members | List, Get, Context Store Search |
| Project Members | List, Get, Context Store Search |
| Releases | List, Get, Context Store Search |
| Tags | List, Get, Context Store Search |
| Group Milestones | List, Get, Context Store Search |
| Project Milestones | List, Get, Context Store Search |
Gitlab API docs
See the official Gitlab API reference.
SDK installation
uv pip install airbyte-agent-sdk
SDK usage
Connectors can run in hosted or open source mode.
Hosted
In hosted mode, API credentials are stored securely in Airbyte Agents. You provide your Airbyte credentials instead.
If your Airbyte client can access multiple organizations, also set organization_id.
This example assumes you've already authenticated your connector with Airbyte. See Authentication to learn more about authenticating. If you need a step-by-step guide, see the hosted execution tutorial.
The connect() factory returns a fully typed GitlabConnector and reads AIRBYTE_CLIENT_ID / AIRBYTE_CLIENT_SECRET from the environment:
- Pydantic AI
- LangChain
- OpenAI Agents
- FastMCP
Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
connector = connect("gitlab", workspace_name="<your_workspace_name>")
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@GitlabConnector.tool_utils
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
connector = connect("gitlab", workspace_name="<your_workspace_name>")
@tool
@GitlabConnector.tool_utils
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
"""Execute Gitlab connector operations."""
result = await connector.execute(entity, action, params or {})
# connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
connector = connect("gitlab", workspace_name="<your_workspace_name>")
# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@GitlabConnector.tool_utils(framework="openai_agents")
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
"""Execute Gitlab connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
agent = Agent(name="Gitlab Assistant", tools=[gitlab_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
connector = connect("gitlab", workspace_name="<your_workspace_name>")
mcp = FastMCP("Gitlab Agent")
@mcp.tool
@GitlabConnector.tool_utils
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
"""Execute Gitlab connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
Or pass credentials explicitly (equivalent, useful when you're not loading them from the environment):
- Pydantic AI
- LangChain
- OpenAI Agents
- FastMCP
Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = GitlabConnector(
auth_config=AirbyteAuthConfig(
workspace_name="<your_workspace_name>",
organization_id="<your_organization_id>", # Optional for multi-org clients
airbyte_client_id="<your-client-id>",
airbyte_client_secret="<your-client-secret>"
)
)
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@GitlabConnector.tool_utils
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = GitlabConnector(
auth_config=AirbyteAuthConfig(
workspace_name="<your_workspace_name>",
organization_id="<your_organization_id>", # Optional for multi-org clients
airbyte_client_id="<your-client-id>",
airbyte_client_secret="<your-client-secret>"
)
)
@tool
@GitlabConnector.tool_utils
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
"""Execute Gitlab connector operations."""
result = await connector.execute(entity, action, params or {})
# connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = GitlabConnector(
auth_config=AirbyteAuthConfig(
workspace_name="<your_workspace_name>",
organization_id="<your_organization_id>", # Optional for multi-org clients
airbyte_client_id="<your-client-id>",
airbyte_client_secret="<your-client-secret>"
)
)
# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@GitlabConnector.tool_utils(framework="openai_agents")
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
"""Execute Gitlab connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
agent = Agent(name="Gitlab Assistant", tools=[gitlab_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = GitlabConnector(
auth_config=AirbyteAuthConfig(
workspace_name="<your_workspace_name>",
organization_id="<your_organization_id>", # Optional for multi-org clients
airbyte_client_id="<your-client-id>",
airbyte_client_secret="<your-client-secret>"
)
)
mcp = FastMCP("Gitlab Agent")
@mcp.tool
@GitlabConnector.tool_utils
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
"""Execute Gitlab connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
Open source
In open source mode, you provide API credentials directly to the connector.
- Pydantic AI
- LangChain
- OpenAI Agents
- FastMCP
Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
from airbyte_agent_sdk.connectors.gitlab.models import GitlabPersonalAccessTokenAuthConfig
connector = GitlabConnector(
auth_config=GitlabPersonalAccessTokenAuthConfig(
access_token="<Log into your GitLab account and generate a personal access token.>"
)
)
agent = Agent("openai:gpt-4o")
@agent.tool_plain
@GitlabConnector.tool_utils
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})
LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
from airbyte_agent_sdk.connectors.gitlab.models import GitlabPersonalAccessTokenAuthConfig
connector = GitlabConnector(
auth_config=GitlabPersonalAccessTokenAuthConfig(
access_token="<Log into your GitLab account and generate a personal access token.>"
)
)
@tool
@GitlabConnector.tool_utils
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
"""Execute Gitlab connector operations."""
result = await connector.execute(entity, action, params or {})
# connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
from airbyte_agent_sdk.connectors.gitlab.models import GitlabPersonalAccessTokenAuthConfig
connector = GitlabConnector(
auth_config=GitlabPersonalAccessTokenAuthConfig(
access_token="<Log into your GitLab account and generate a personal access token.>"
)
)
# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@GitlabConnector.tool_utils(framework="openai_agents")
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
"""Execute Gitlab connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
agent = Agent(name="Gitlab Assistant", tools=[gitlab_execute])
FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.gitlab import GitlabConnector
from airbyte_agent_sdk.connectors.gitlab.models import GitlabPersonalAccessTokenAuthConfig
connector = GitlabConnector(
auth_config=GitlabPersonalAccessTokenAuthConfig(
access_token="<Log into your GitLab account and generate a personal access token.>"
)
)
mcp = FastMCP("Gitlab Agent")
@mcp.tool
@GitlabConnector.tool_utils
async def gitlab_execute(entity: str, action: str, params: dict | None = None):
"""Execute Gitlab connector operations."""
result = await connector.execute(entity, action, params or {})
return result.model_dump(mode="json") if hasattr(result, "model_dump") else result
Authentication
For all authentication options, see the connector's authentication documentation.
Version information
Connector version: 1.0.4