Shows commit history
AI agents call git-log to retrieve information from GitHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
git-log retrieves and displays commit history without modifying, creating, or deleting any data. It is a read-only operation that poses minimal security risk even if invoked by an AI agent, as it cannot alter the repository or execute arbitrary operations. The main concern would be information disclosure (e.g., revealing sensitive commit messages), but that is lower severity than write or destructive operations.
From the tool's definition Tool name 'git-log' and description 'Shows commit history' indicate a query/retrieval operation with no mutation of repository state.
Attacks that exploit this kind of access
Shows commit history. It is categorised as a Read tool in the GitHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for git-log: 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 GitHub MCP Server. Nothing to install.
git-log 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-log 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-log. 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-log is provided by the GitHub MCP Server MCP server (jungchihoon/github-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 →