AI agents invoke hg_evolve to trigger actions in Mercurial. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
hg evolve is a Mercurial command that automatically resolves unstable changesets by rewriting history (rebasing, updating, or obsoleting changesets). This constitutes a complex execution that modifies repository state in potentially far-reaching ways.
From the tool's definition 'Evolves the repository to resolve instabilities' — triggers the Mercurial evolve operation which rewrites and reorganizes changesets, altering repository history
Attacks that exploit this kind of access
Evolves the repository to resolve instabilities. It is categorised as a Execute tool in the Mercurial MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mercurial MCP server in PolicyLayer and add a rule for hg_evolve: 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_evolve is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the hg_evolve 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_evolve. 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_evolve 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 →