Performance metrics (impressions, clicks, spend, CTR, CPC, CPM, conversions). Works at account, campaign, ad set, or ad level. Provide either a date_preset OR a time_range.
AI agents call get_insights to retrieve information from Claude Meta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves analytics and performance data from Meta Ads accounts. It queries existing metrics without creating, modifying, deleting, or executing operations. The worst-case misuse would be unauthorized access to performance data, which is a read-level confidentiality concern rather than integrity or availability risk.
From the tool's definition Tool name is 'get_insights' and description states it retrieves 'Performance metrics (impressions, clicks, spend, CTR, CPC, CPM, conversions)' at various levels.
Attacks that exploit this kind of access
Performance metrics (impressions, clicks, spend, CTR, CPC, CPM, conversions). Works at account, campaign, ad set, or ad level. Provide either a date_preset OR a time_range. It is categorised as a Read tool in the Claude Meta MCP Server, which means it retrieves data without modifying state.
Register the Claude Meta MCP server in PolicyLayer and add a rule for get_insights: 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 Claude Meta. Nothing to install.
get_insights 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 get_insights 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 get_insights. 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.
get_insights is provided by the Claude Meta MCP server (maxx3250/claude-meta-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 →