Run git-memory CLI status command and return JSON
AI agents call git_status_cli to retrieve information from Git Memory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The git status command is a read-only operation that reports the current state of a Git repository (unstaged changes, untracked files, branch information, etc.). It has no side effects and does not create, modify, delete, or execute external operations. The function returns JSON representation of status data, confirming its informational nature.
From the tool's definition Tool name 'git_status_cli' and description 'Run git-memory CLI status command and return JSON' indicate a query operation that retrieves repository status information without modifying data.
Attacks that exploit this kind of access
Run git-memory CLI status command and return JSON. It is categorised as a Read tool in the Git Memory MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Git Memory MCP Server MCP server in PolicyLayer and add a rule for git_status_cli: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Git Memory MCP Server. Nothing to install.
git_status_cli is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the git_status_cli rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for git_status_cli. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
git_status_cli is provided by the Git Memory MCP Server MCP server (nirutyodjai/git-memory-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →