AI agents call changeset to retrieve information from Selvedge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the context strongly suggests changeset retrieves or assembles a set of related changes—a read operation analogous to blame, diff, and history. There is no indication it modifies, deletes, or executes external actions.
From the tool's definition Tool name 'changeset' in a change-tracking system with sibling query tools (blame, diff, history, search) and no description.
Documented attack patterns abuse exactly the kind of access changeset gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Selvedge, and nothing reaches the server without passing your rules. This is the rule we recommend for changeset:
{
"version": "1",
"default": "deny",
"tools": {
"changeset": {}
}
}changeset is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
changeset. It is categorised as a Read tool in the Selvedge MCP Server, which means it retrieves data without modifying state.
Register the Selvedge MCP server in PolicyLayer and add a rule for changeset: 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 Selvedge. Nothing to install.
changeset 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 changeset 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 changeset. 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.
changeset is provided by the Selvedge MCP server (masondelan/selvedge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Selvedge, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Selvedge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.