AI agents call hg_log to retrieve information from Mercurial without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The hg_log tool retrieves and displays commit history from a Mercurial repository. This is purely informational and read-only; it does not create, modify, delete, or execute any operations. There is no blast radius from misuse—an AI agent cannot harm the repository or system by querying logs. Severity is low because viewing commit history poses minimal risk.
From the tool's definition Tool name is 'hg_log' and description states 'Shows the commit history' — this is a query operation that retrieves historical data without modification or side effects.
Attacks that exploit this kind of access
Shows the commit history. It is categorised as a Read tool in the Mercurial MCP Server, which means it retrieves data without modifying state.
Register the Mercurial MCP server in PolicyLayer and add a rule for hg_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 Mercurial. Nothing to install.
hg_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 hg_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 hg_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.
hg_log is provided by the Mercurial MCP server (metal-shark-sharktech/mcp-server-mercurial). 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 →