**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, ...
Accepts freeform code/query input (query); Single-target operation; Admin/system-level operation
Part of the Sfmc MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
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.
tools:
search_mce_help:
rules:
- action: allowSee the full Sfmc policy for all 11 tools.
Agents calling read-class tools like search_mce_help have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
**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.
Add a rule in your Intercept YAML policy under the tools section for search_mce_help. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Sfmc MCP server.
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 Intercept 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 Intercept 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). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept