AI agents call getChangesByUser to retrieve information from Weblate MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical change data for audit or reporting purposes. It has no side effects, does not modify any translations or project state, and poses minimal risk if called by an AI agent. The read-only nature and the context of other tools on the server (which include write/bulk operations as separate tools) confirm this is purely informational.
From the tool's definition Tool name 'getChangesByUser' and description 'Get recent changes by a specific user' indicate a retrieval operation with no modification capability.
Documented attack patterns abuse exactly the kind of access getChangesByUser gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Weblate MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for getChangesByUser:
{
"version": "1",
"default": "deny",
"tools": {
"getChangesByUser": {}
}
} getChangesByUser 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.
Get recent changes by a specific user. It is categorised as a Read tool in the Weblate MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Weblate MCP Server MCP server in PolicyLayer and add a rule for getChangesByUser: 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 Weblate MCP Server. Nothing to install.
getChangesByUser 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 getChangesByUser 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 getChangesByUser. 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.
getChangesByUser is provided by the Weblate MCP Server MCP server (mmntm/weblate-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Weblate MCP Server, 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.
20 Weblate MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.