Skip to main content
Glama
MementoRC

MCP Git Server

by MementoRC

git_diff_unstaged

Identify uncommitted changes in your Git working directory with this tool. Review modifications before staging them to ensure accurate commit management.

Instructions

Shows changes in the working directory that are not yet staged

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repo_pathYes

Implementation Reference

  • Core handler function that executes `repo.git.diff()` to show unstaged changes, with options for stat-only, name-only, paths, and size limiting.
    def git_diff_unstaged(
        repo: Repo,
        stat_only: bool = False,
        max_lines: int | None = None,
        name_only: bool = False,
        paths: list[str] | None = None,
    ) -> str:
        """Get unstaged changes diff with file-specific and advanced options"""
        try:
            # Build git diff arguments
            diff_args = []
    
            # Add options based on parameters
            if name_only:
                diff_args.append("--name-only")
            elif stat_only:
                diff_args.append("--stat")
    
            # Add specific paths if provided
            if paths:
                diff_args.extend(["--"] + paths)
    
            # Execute git diff with arguments
            diff_output = repo.git.diff(*diff_args)
    
            # Handle name-only output
            if name_only:
                return (
                    f"Files with unstaged changes:\n{diff_output}"
                    if diff_output.strip()
                    else "No unstaged changes"
                )
    
            # Handle stat-only output
            if stat_only:
                return (
                    f"Unstaged changes summary:\n{diff_output}"
                    if diff_output.strip()
                    else "No unstaged changes"
                )
    
            # Apply size limiting for full diff output
            return _apply_diff_size_limiting(
                diff_output, "unstaged changes", stat_only, max_lines
            )
    
        except GitCommandError as e:
            return f"❌ Diff unstaged failed: {str(e)}"
        except Exception as e:
            return f"❌ Diff unstaged error: {str(e)}"
  • Pydantic input schema/model defining parameters for the git_diff_unstaged tool.
    class GitDiffUnstaged(BaseModel):
        repo_path: str
        stat_only: bool | None = False
        max_lines: int | None = None
        name_only: bool | None = False
        paths: list[str] | None = None
  • Tool registration in the CallToolHandler._get_git_handlers() method, creating a wrapped handler for git_diff_unstaged.
    "git_diff_unstaged": self._create_git_handler(
        git_diff_unstaged,
        requires_repo=True,
        extra_args=["stat_only", "max_lines", "name_only", "paths"],
    ),
  • ToolDefinition registration in ToolRegistry.initialize_default_tools(), defining name, description, schema, and metadata for git_diff_unstaged.
    ToolDefinition(
        name=GitTools.DIFF_UNSTAGED,
        category=ToolCategory.GIT,
        description="Show changes in the working directory that are not yet staged",
        schema=GitDiffUnstaged,
        handler=placeholder_handler,
        requires_repo=True,
  • Helper function used by git_diff_unstaged (and other diff functions) to apply output truncation and size warnings.
    def _apply_diff_size_limiting(
        diff_output: str,
        operation_name: str,
        stat_only: bool = False,
        max_lines: int | None = None,
    ) -> str:
        """Apply size limiting to diff outputs with consistent formatting"""
        if not diff_output.strip():
            return f"No changes detected in {operation_name}"
    
        if stat_only:
            # This should be handled by the caller using --stat flag
            return diff_output
    
        # Apply line limit if specified
        if max_lines and max_lines > 0:
            lines = diff_output.split("\n")
            if len(lines) > max_lines:
                truncated_output = "\n".join(lines[:max_lines])
                truncated_output += (
                    f"\n\n... [Truncated: showing {max_lines} of {len(lines)} lines]"
                )
                truncated_output += "\nUse stat_only=true for summary or increase max_lines for more content"
                return truncated_output
    
        # Check if output is extremely large and warn
        if len(diff_output) > 50000:  # 50KB threshold
            lines_count = len(diff_output.split("\n"))
            warning = f"⚠️  Large diff detected ({lines_count} lines, ~{len(diff_output) // 1000}KB)\n"
            warning += "Consider using stat_only=true for summary or max_lines parameter to limit output\n\n"
            return warning + diff_output
    
        return diff_output
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It describes what the tool does but doesn't mention output format, whether it shows full diffs or summaries, potential side effects, or error conditions. 'Shows changes' is vague about behavioral characteristics.

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

Conciseness5/5

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

Single sentence, zero waste, front-loaded with the core purpose. Every word earns its place in conveying the essential function.

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?

For a single-parameter tool with no annotations and no output schema, the description adequately states what it does but lacks details about output format, error handling, or behavioral nuances. It's complete enough for basic understanding but leaves operational questions unanswered.

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 doesn't mention parameters at all, but with only 1 parameter and 0% schema description coverage, the baseline would be lower. However, the tool name and description strongly imply the repo_path parameter context, providing meaningful semantic context beyond the bare schema.

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

Purpose4/5

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

The description clearly states the verb 'shows' and the resource 'changes in the working directory' with the specific condition 'that are not yet staged'. It distinguishes from sibling git_diff_staged by specifying unstaged changes, but doesn't explicitly differentiate from git_diff which might show both staged and unstaged changes.

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

Usage Guidelines3/5

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

The description implies usage context (when you want to see unstaged changes) but doesn't provide explicit guidance on when to use this versus alternatives like git_diff or git_status. No exclusions or prerequisites are mentioned.

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

Related 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/MementoRC/mcp-git'

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