Get traffic sources - where your visitors are coming from.
AI agents call savri_get_referrers to retrieve information from Savri Analytics MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries analytics data about referral sources without creating, modifying, deleting, or executing any operations. It has no side effects and poses minimal security risk even if misused by an AI agent, as it only returns historical visitor traffic source information.
From the tool's definition Tool name 'savri_get_referrers' and description 'Get traffic sources - where your visitors are coming from' indicate data retrieval only. The verb 'Get' and absence of modification language confirm read-only operation.
Attacks that exploit this kind of access
Get traffic sources - where your visitors are coming from. It is categorised as a Read tool in the Savri Analytics MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Savri Analytics MCP Server MCP server in PolicyLayer and add a rule for savri_get_referrers: 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 Savri Analytics MCP Server. Nothing to install.
savri_get_referrers 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 savri_get_referrers 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 savri_get_referrers. 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.
savri_get_referrers is provided by the Savri Analytics MCP Server MCP server (savri-io/mcp). 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 →