Envia um e-mail transacional para um único destinatário. Por padrão executa um pre-flight automático antes do envio: valida a definition, o asset do Content Builder, os content blocks referenciados, os atributos obrigatórios (campos isRequired da DE + AMPscript + RaiseError guards) e normaliza os...
Part of the Ljit Mcp Sfmc server.
Free to start. No card required.
AI agents use txn_send_email to create or modify resources in Ljit Mcp Sfmc. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call txn_send_email repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Ljit Mcp Sfmc.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"txn_send_email": {
"limits": [
{
"counter": "txn_send_email_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Ljit Mcp Sfmc policy for all 40 tools.
These attack patterns abuse exactly the kind of access txn_send_email gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Envia um e-mail transacional para um único destinatário. Por padrão executa um pre-flight automático antes do envio: valida a definition, o asset do Content Builder, os content blocks referenciados, os atributos obrigatórios (campos isRequired da DE + AMPscript + RaiseError guards) e normaliza os nomes de atributos contra o schema da DE. Se houver erros bloqueantes, o e-mail NÃO é enviado e o relatório de pre-flight é retornado com sent=false e a lista de correções necessárias. Use skipPreflight=true apenas para envios de produção onde a validação já foi feita. O messageKey é opcional e será gerado automaticamente se não informado. IMPORTANTE: Para envios de teste onde é necessário confirmar a entrega real, use txn_send_test_email, que além do pre-flight completo aguarda a confirmação de status do SFMC antes de reportar sucesso.. It is categorised as a Write tool in the Ljit Mcp Sfmc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ljit Mcp Sfmc MCP server in PolicyLayer and add a rule for txn_send_email: 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.
txn_send_email is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the txn_send_email 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 txn_send_email. 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.
txn_send_email 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.
Deterministic rules across all 40 Ljit Mcp Sfmc tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.