AI agents call git_log to retrieve information from Context 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 from a Git repository. This is a pure read operation that queries existing data without modifying, deleting, or executing any code. The tool only presents historical information already recorded in the repository. The blast radius of misuse is minimal—an agent cannot cause harm by viewing commit history.
From the tool's definition Tool description: 'Show recent commit history — hash, author, date, message.' The verb 'show' and the list of read-only commit metadata (hash, author, date, message) indicate a query operation with no side effects.
Attacks that exploit this kind of access
Show recent commit history — hash, author, date, message. It is categorised as a Read tool in the Context MCP Server, which means it retrieves data without modifying state.
Register the Context 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 Context. 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 Context MCP server (vibhasdutta/context-mcp). 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 →