Resumo agregado (aproximação de painel) sobre uma amostra de usuários exportados: engagement score (média/min/máx/distribuição), atividade (ativos vs inativos por lastActivity, média de ações) e top segmentos por nº de usuários. É derivado do export, calculado client-side — NÃO são os KPIs nativo...
AI agents call pers_metrics_summary to retrieve information from Ljit Mcp Sfmc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
filter | string | — | Nome ou ID de segmento para limitar a amostra |
dataset | string | — | Dataset alvo (padrão: MCP_PERS_DATASET) |
pageSize | number | — | Tamanho de página do export (padrão: 200, máx: 1000) |
segmentId | string | — | ID do segmento |
maxRecords | number | — | Teto de registros agregados (padrão: 1000, máx: 50000) |
activeWithinDays | number | — | Janela em dias para considerar "ativo" pela lastActivity (padrão: 30) |
Parameters from the server's own tool schema.
The tool explicitly states it is read-only ('Somente leitura'), derives data from an export calculated client-side, and only summarizes engagement/activity metrics. No writes, executions, or destructive actions are involved.
From the tool's definition Somente leitura (Read-only). 'É derivado do export, calculado client-side' and 'Resumo agregado... sobre uma amostra de usuários exportados' — retrieves and aggregates metrics without any side effects.
Attacks that exploit this kind of access
Resumo agregado (aproximação de painel) sobre uma amostra de usuários exportados: engagement score (média/min/máx/distribuição), atividade (ativos vs inativos por lastActivity, média de ações) e top segmentos por nº de usuários. É derivado do export, calculado client-side — NÃO são os KPIs nativos do Dashboard (revenue/conversão/impressões não têm API). Limitado por maxRecords; truncated=true indica que há mais dados além da amostra. Use filter/segmentId para focar um segmento. Somente leitura. It is categorised as a Read tool in the Ljit Mcp Sfmc MCP Server, which means it retrieves data without modifying state.
pers_metrics_summary accepts 6 parameters: filter, dataset, pageSize, segmentId, maxRecords, activeWithinDays. The full parameter table on this page comes from the server's own tool schema.
Register the Ljit Mcp Sfmc MCP server in PolicyLayer and add a rule for pers_metrics_summary: 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 Ljit Mcp Sfmc. Nothing to install.
pers_metrics_summary 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 pers_metrics_summary 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 pers_metrics_summary. 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.
pers_metrics_summary is provided by the Ljit Mcp Sfmc MCP server (ljit-mcp-sfmc). 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 →