Skip to main content
Glama
Sign In
Secure Git MCP

Secure Git MCP

by IvanAbramovichWork
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

git_unstage

DestructiveIdempotent

Unstage selected files from the Git index without modifying working files or unrelated index entries, while enforcing configured repository and project path policies.

Instructions

Unstage a permitted literal selection without changing working files or unrelated index entries. Omit repo_path to use the configured repository. Results and operations are restricted according to project policy.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "files": "<files>"
    },
    "name": "git_unstage"
  }
}

Input Schema

NameRequiredDescriptionDefault
filesYes
repo_pathNoOptional repository root. Omit to use the server's fixed repository. An explicit path must identify that same repository.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2026.10.19

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already declare this as mutating, destructive, and idempotent; the description adds meaningful scope by saying it will not change working files or unrelated index entries. The mention of project policy also adds useful authorization context beyond the structured fields. It stops short of describing error behavior or what happens when a file is not staged.

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 short and front-loads the operation and its scoping constraints. The phrase 'permitted literal selection' is slightly awkward, but overall it is efficient and easy to parse.

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?

Annotations already cover the mutation profile and the schema documents repo_path, so the description need not repeat those. However, for a destructive mutation tool with no output schema, it leaves important gaps around error cases, the exact interpretation of files, and what happens when entries are not staged.

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

Parameters3/5

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

Schema coverage is only 50%, and the files parameter has no schema description. The phrase 'literal selection' adds some meaning about how file arguments are interpreted, but it is vague and does not compensate fully for the undocumented files parameter.

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?

States a specific verb and resource (unstage a selection) and clarifies that working files and unrelated index entries are untouched. It does not explicitly distinguish itself from siblings like git_reset or git_restore, which is the main clarity gap.

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?

Provides usage guidance only for the repo_path parameter, not for when to choose this tool over alternatives such as git_reset or git_restore. There is no statement of when not to use it or what preconditions apply.

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

Deploy Server

Other Tools