AI agents call hg_diff_staged 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.
hg_diff_staged retrieves and displays diff information about uncommitted changes in a Mercurial repository. This is a read-only operation with no side effects—it queries repository state without modifying, executing, or destroying data. The low severity reflects minimal blast radius: an AI agent cannot cause harm by examining diffs.
From the tool's definition Tool shows 'uncommitted changes' with no modification capability. Description explicitly states it displays changes without implying any write, delete, or execute operations.
Attacks that exploit this kind of access
Shows all uncommitted changes (Mercurial has no staging area). 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_staged: 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_staged 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_staged 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_staged. 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_staged 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 →