Skip to main content
Glama
modelcontextprotocol

git MCP server

Official

git_show

Read-onlyIdempotent

Display the complete contents of a Git commit, including file changes and metadata, by specifying repository path and revision.

Instructions

Shows the contents of a commit

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
repo_pathYes
revisionYes

Implementation Reference

  • The git_show handler function that executes the tool logic. It validates the revision, retrieves the commit, formats commit metadata (SHA, author, date, message), computes the diff against its parent (or NULL_TREE for the initial commit), and returns the combined output as a string.
    def git_show(repo: git.Repo, revision: str) -> str:
        # Defense in depth: reject revisions starting with '-' to prevent flag injection,
        # even if a malicious ref with that name exists (e.g. via filesystem manipulation)
        if revision.startswith("-"):
            raise BadName(f"Invalid revision: '{revision}' - cannot start with '-'")
        commit = repo.commit(revision)
        output = [
            f"Commit: {commit.hexsha!r}\n"
            f"Author: {commit.author!r}\n"
            f"Date: {commit.authored_datetime!r}\n"
            f"Message: {commit.message!r}\n"
        ]
        if commit.parents:
            parent = commit.parents[0]
            diff = parent.diff(commit, create_patch=True)
        else:
            diff = commit.diff(git.NULL_TREE, create_patch=True)
        for d in diff:
            output.append(f"\n--- {d.a_path}\n+++ {d.b_path}\n")
            if d.diff is None:
                continue
            if isinstance(d.diff, bytes):
                output.append(d.diff.decode('utf-8'))
            else:
                output.append(d.diff)
        return "".join(output)
  • The GitShow Pydantic model defining the input schema for the git_show tool, with fields repo_path (str) and revision (str).
    class GitShow(BaseModel):
        repo_path: str
        revision: str
  • Registration of the git_show tool in the list_tools handler, using GitTools.SHOW enum, with description 'Shows the contents of a commit' and inputSchema from GitShow.model_json_schema().
    Tool(
        name=GitTools.SHOW,
        description="Shows the contents of a commit",
        inputSchema=GitShow.model_json_schema(),
        annotations=ToolAnnotations(
            readOnlyHint=True,
            destructiveHint=False,
            idempotentHint=True,
            openWorldHint=False,
        ),
    ),
  • Enum definition GitTools.SHOW = 'git_show' providing the string name used to identify the tool.
    SHOW = "git_show"
  • The call_tool handler that dispatches 'git_show' (GitTools.SHOW) by calling git_show(repo, arguments['revision']) and returning the result as TextContent.
    case GitTools.SHOW:
        result = git_show(repo, arguments["revision"])
        return [TextContent(
            type="text",
            text=result
        )]
Behavior2/5

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds minimal behavioral context beyond 'shows', not elaborating on what 'contents' entails (e.g., diff, metadata).

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

Conciseness4/5

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

The description is a single, concise sentence of 6 words with no filler. It is front-loaded but may sacrifice detail for brevity.

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?

Despite the tool's simplicity, the description omits parameter explanations, return format (no output schema), and usage context. It provides the core purpose but is insufficient for correct invocation.

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

Parameters1/5

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

Schema description coverage is 0%, with no parameter descriptions in the schema. The description does not mention repo_path or revision, leaving their purpose and format entirely unexplained.

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 'Shows the contents of a commit' clearly states a specific verb and resource (contents of a commit). It differentiates from siblings like git_log (list commits) and git_diff (differences), though it doesn't explicitly contrast them.

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 on when to use this tool versus siblings such as git_diff or git_log. The description does not mention prerequisites or exclusions, leaving the agent without 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/modelcontextprotocol/git'

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