Skip to main content
Glama

create_project

Set up a new GitLab project by specifying a name, optional description, and visibility level such as private, internal, or public.

Instructions

Create a new GitLab project.

Args:
    name: Project name
    description: Project description (optional)
    visibility: Project visibility (private, internal, public)
    token: GitLab Personal Access Token (optional)
    ctx: MCP context (automatically injected)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
descriptionNo
visibilityNoprivate
tokenNo
ctxNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The 'create_project' tool handler function. It creates a new GitLab project by calling the GitLab API POST /projects endpoint. Parameters: name (required), description (optional), visibility (optional, defaults to 'private'), token (optional), ctx (auto-injected MCP context). It sends a POST request with project data to GitLab and returns the created project's name, ID, and URL.
    @mcp.tool()
    async def create_project(name: str, description: str = "", visibility: str = "private", token: str = None, ctx=None) -> str:
        """Create a new GitLab project.
        
        Args:
            name: Project name
            description: Project description (optional)
            visibility: Project visibility (private, internal, public)
            token: GitLab Personal Access Token (optional)
            ctx: MCP context (automatically injected)
        """
        data = {
            "name": name,
            "description": description,
            "visibility": visibility,
            "initialize_with_readme": True
        }
        
        result = await make_gitlab_request("/projects", "POST", data, ctx, token=token)
        
        if isinstance(result, dict) and "error" in result:
            return f"Error creating project: {result['error']}"
        
        return f"Project created: {result['name']} (ID: {result['id']})\nURL: {result['web_url']}"
  • The tool is registered using the @mcp.tool() decorator on the FastMCP instance 'mcp' (line 9: mcp = FastMCP('GitLab MCP Server', ...)). The decorator registers 'create_project' as an MCP tool within the FastMCP framework.
    @mcp.tool()
    async def create_project(name: str, description: str = "", visibility: str = "private", token: str = None, ctx=None) -> str:
  • Helper function called by create_project to execute the actual HTTP request to the GitLab API. It handles token resolution (from parameter, context headers, or environment variable), builds the GitLab API URL, and executes GET/POST/PUT/DELETE requests using httpx.
    async def make_gitlab_request(endpoint: str, method: str = "GET", data: dict = None, ctx=None, token: str = None) -> dict[str, Any] | None:
        """Make a request to GitLab API with proper error handling."""
        # Priority: 1. Explicit token parameter, 2. Context headers, 3. Environment variable
        
        # If no explicit token provided, try to get from context
        if not token and ctx and hasattr(ctx, 'request_context') and ctx.request_context:
            # Try to get from request headers
            if hasattr(ctx.request_context, 'headers'):
                token = ctx.request_context.headers.get('GITLAB_TOKEN')
        
        # Fallback to environment variable
        if not token:
            token = os.getenv("GITLAB_TOKEN")
        
        if not token:
            return {"error": "GitLab token not provided. Please provide a token parameter, GITLAB_TOKEN in the request headers, or set the environment variable."}
        
        # Get GitLab URL (from context or environment)
        gitlab_url = os.getenv("GITLAB_URL", "https://gitlab.com")
        
        headers = {
            "PRIVATE-TOKEN": token,
            "Content-Type": "application/json"
        }
        
        url = f"{gitlab_url}/api/v4{endpoint}"
        
        async with httpx.AsyncClient() as client:
            try:
                if method == "GET":
                    response = await client.get(url, headers=headers, timeout=30.0)
                elif method == "POST":
                    response = await client.post(url, headers=headers, json=data, timeout=30.0)
                elif method == "PUT":
                    response = await client.put(url, headers=headers, json=data, timeout=30.0)
                elif method == "DELETE":
                    response = await client.delete(url, headers=headers, timeout=30.0)
                
                response.raise_for_status()
                return response.json() if response.content else {"success": True}
            except Exception as e:
                return {"error": str(e)}
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, and the description does not disclose behavioral traits like authentication requirements, idempotency, or side effects beyond creation. The token parameter is mentioned as optional, but no clarity on what happens if omitted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description uses a clear structure with 'Args:' but includes the `ctx` parameter which is automatically injected, adding unnecessary detail. It could be more concise by omitting obvious parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers all parameters and provides an output schema (presumably for the project object), but lacks guidance on usage context. For a creation tool, it is minimally complete but not exceptional.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaning to all five parameters (name, description, visibility, token, ctx) beyond the input schema's titles and defaults. It explains the role of each parameter, compensating for the 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Create' and the resource 'GitLab project', making the action unambiguous. It effectively distinguishes from sibling tools like archive_project, delete_project, and fork_project.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as fork_project or transfer_project. The description lacks any context about prerequisites or scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/skmprb/gitlab-clone-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server