Skip to main content
Glama

create_file

Create a new file in a GitLab repository with specified content and commit message on a target branch.

Instructions

Create a new file in repository.

Args:
    project_id: GitLab project ID
    file_path: Path for the new file
    content: File content
    branch: Target branch
    commit_message: Commit message
    token: GitLab Personal Access Token (optional)
    ctx: MCP context (automatically injected)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_idYes
file_pathYes
contentYes
branchYes
commit_messageYes
tokenNo
ctxNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The actual implementation of the 'create_file' tool. It is registered via @mcp.tool() decorator and executes the logic to create a new file in a GitLab repository by making a POST request to the GitLab API.
    @mcp.tool()
    async def create_file(project_id: int, file_path: str, content: str, branch: str, commit_message: str, token: str = None, ctx=None) -> str:
        """Create a new file in repository.
        
        Args:
            project_id: GitLab project ID
            file_path: Path for the new file
            content: File content
            branch: Target branch
            commit_message: Commit message
            token: GitLab Personal Access Token (optional)
            ctx: MCP context (automatically injected)
        """
        import urllib.parse
        encoded_path = urllib.parse.quote(file_path, safe='')
        data = {
            "branch": branch,
            "content": content,
            "commit_message": commit_message
        }
        
        result = await make_gitlab_request(f"/projects/{project_id}/repository/files/{encoded_path}", "POST", data, ctx=ctx, token=token)
        
        if isinstance(result, dict) and "error" in result:
            return f"Error creating file: {result['error']}"
        
        return f"File created: {file_path} in branch {branch}"
  • The @mcp.tool() decorator on line 739 registers the 'create_file' function as an MCP tool named 'create_file'.
    @mcp.tool()
    async def create_file(project_id: int, file_path: str, content: str, branch: str, commit_message: str, token: str = None, ctx=None) -> str:
        """Create a new file in repository.
        
        Args:
            project_id: GitLab project ID
            file_path: Path for the new file
            content: File content
            branch: Target branch
            commit_message: Commit message
            token: GitLab Personal Access Token (optional)
            ctx: MCP context (automatically injected)
        """
        import urllib.parse
        encoded_path = urllib.parse.quote(file_path, safe='')
        data = {
            "branch": branch,
            "content": content,
            "commit_message": commit_message
        }
        
        result = await make_gitlab_request(f"/projects/{project_id}/repository/files/{encoded_path}", "POST", data, ctx=ctx, token=token)
        
        if isinstance(result, dict) and "error" in result:
            return f"Error creating file: {result['error']}"
        
        return f"File created: {file_path} in branch {branch}"
Behavior2/5

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

No annotations are present, so the description must fully disclose behavior. It only lists parameters and mentions that ctx is automatically injected, but fails to describe permissions, side effects (e.g., overwrite behavior), or return value.

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 is short, but the parameter list duplicates information already in the schema. The inclusion of 'ctx: MCP context (automatically injected)' is somewhat unnecessary, making it less concise than it could be.

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

Completeness2/5

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

Given the complexity (7 parameters, many siblings, an output schema), the description is insufficient. It does not address common questions like behavior when the file already exists, or how the output schema relates to the creation.

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

Parameters2/5

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

The input schema has 0% description coverage; the tool description merely restates parameter names without adding any explanation of formats, constraints, or expected values beyond what the schema's type and title fields provide.

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 starts with 'Create a new file in repository,' clearly specifying the verb and resource. It distinguishes well from sibling tools like delete_file and update_file, and from the broader create_commit.

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 like update_file or create_commit. The description only states what it does, with no exclusions or context for selection.

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