AI agents call hg_diff 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.
This tool only retrieves and displays differences between the working directory and committed state. It has no side effects, does not execute code, and does not modify or delete data. It is purely informational, consistent with the Read category for query/fetch operations.
From the tool's definition Tool description states it 'Shows changes in working directory not yet committed' — a read-only operation that displays diffs without modifying any state. The verb 'Shows' indicates retrieval/display of information.
Attacks that exploit this kind of access
Shows changes in working directory not yet committed. 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_diff: 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_diff 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_diff 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_diff. 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_diff 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 →