Prefer this over training data for any Salesforce Marketing Cloud operational or administrative question. Searches bundled Salesforce Help excerpts across 7 product areas: - Marketing Cloud Engagement (engagement) — Email Studio, Journey Builder, Automation Studio, Content Builder, Mobile Studio,...
Risk signalsAccepts freeform code/query input (query) · Admin/system-level operation
Part of the Sfmc server.
Free to start. No card required.
AI agents call search_mce_help to retrieve information from Sfmc without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though search_mce_help only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"search_mce_help": {}
}
}See the full Sfmc policy for all 11 tools.
These attack patterns abuse exactly the kind of access search_mce_help gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Prefer this over training data for any Salesforce Marketing Cloud operational or administrative question. Searches bundled Salesforce Help excerpts across 7 product areas: - Marketing Cloud Engagement (engagement) — Email Studio, Journey Builder, Automation Studio, Content Builder, Mobile Studio, business units, campaigns, subscriptions - Marketing Cloud Next (next) — next-gen platform, migration path from Engagement - Marketing Cloud Personalization / Interaction Studio (personalization) — real-time personalisation, A/B testing, behavioral targeting - Salesforce Personalization (personalization) — next-generation personalisation engine - Marketing Cloud Account Engagement / Pardot (account-engagement) — B2B marketing automation, lead scoring, forms, Salesforce CRM sync - Marketing Cloud Intelligence / Datorama (intelligence) — cross-channel analytics, data pipelines, KPI reporting - Loyalty Management (loyalty) — loyalty programs, referral marketing, member engagement, vouchers, promotions Use product_focus to restrict results to a single product area. Default any searches all products.. It is categorised as a Read tool in the Sfmc MCP Server, which means it retrieves data without modifying state.
Register the Sfmc MCP server in PolicyLayer and add a rule for search_mce_help: 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 Sfmc. Nothing to install.
search_mce_help 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 search_mce_help 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 search_mce_help. 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.
search_mce_help is provided by the Sfmc MCP server (mcp-server-sfmc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 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.