Execute a saved Salesforce Analytics report by ID and return the results as structured rows. Optionally apply on-the-fly filters (column, operator, value). Returns the factMap data parsed into an array of row objects. Use sf_get_report_metadata first to understand available columns.
AI agents invoke sf_run_report to trigger actions in Salesforce Marketing. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
filters | array | — | |
reportId | string | Yes | Salesforce Report ID |
Parameters from the server's own tool schema.
Although report execution itself is read-only in outcome (returns data), the tool permits dynamic parameterization via filters that could be manipulated to access unintended data subsets or trigger expensive operations. The ability to 'execute' with variable inputs on external systems classifies this as Execute rather than Read.
From the tool's definition Tool name includes 'run_report' and description states 'Execute a saved Salesforce Analytics report by ID' — the word 'Execute' combined with dynamic filter application ('apply on-the-fly filters') indicates this triggers report execution with user-controlled…
Attacks that exploit this kind of access
Execute a saved Salesforce Analytics report by ID and return the results as structured rows. Optionally apply on-the-fly filters (column, operator, value). Returns the factMap data parsed into an array of row objects. Use sf_get_report_metadata first to understand available columns. It is categorised as a Execute tool in the Salesforce Marketing MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
sf_run_report accepts 2 parameters: filters, reportId. Required: reportId. The full parameter table on this page comes from the server's own tool schema.
Register the Salesforce Marketing MCP server in PolicyLayer and add a rule for sf_run_report: 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 Salesforce Marketing. Nothing to install.
sf_run_report is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sf_run_report 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 sf_run_report. 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.
sf_run_report is provided by the Salesforce Marketing MCP server (salesforce-marketing-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 →