AI agents use hg_commit to create or update resources in Mercurial — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mercurial environment.
hg_commit modifies repository state by creating new commits. This is a Write operation rather than Execute because its primary purpose is data persistence, not arbitrary code execution. While it can trigger hooks and has effects beyond simple data modification, the core action is creating/modifying repository records.
From the tool's definition Tool name 'hg_commit' and description 'Records changes to the repository' indicate this creates a permanent commit (revision) in version control.
Attacks that exploit this kind of access
Records changes to the repository. It is categorised as a Write tool in the Mercurial MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mercurial MCP server in PolicyLayer and add a rule for hg_commit: 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_commit is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the hg_commit 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_commit. 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_commit 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 →