sf_get_flow_errors
Retrieves Flow interview fault records from the FlowRecordRelation and FlowInterview objects. Shows flows that have errored in runtime with their fault message and the record that triggered the error. flowApiName: filter to a specific flow API name (optional — returns errors for all flows if omit...
This record as markdown: /tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-get-flow-errors.md
What sf_get_flow_errors does on Salesforce Metadata Mcp
AI agents call sf_get_flow_errors to retrieve information from Salesforce Metadata Mcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why sf_get_flow_errors is rated Low
This tool queries existing error records from Salesforce metadata objects (FlowRecordRelation and FlowInterview) with read-only access. It has no side effects, creates no data, and cannot trigger flows or modify any state. The blast radius of misuse is minimal—an unauthorized user could view error details from flows, but cannot alter system state or perform destructive actions.
From the tool's definition Tool description states 'Retrieves Flow interview fault records' and 'Shows flows that have errored in runtime'. The parameters (flowApiName, lookbackHours, limit) are all filtering/query options.
Attacks that exploit this kind of access
The rule that runs sf_get_flow_errors safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Salesforce Metadata Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sf_get_flow_errors, this is the rule to start with:
sf_get_flow_errors is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Salesforce Metadata Mcp, apply this rule, and every sf_get_flow_errors call is checked against it from then on.
Questions about sf_get_flow_errors
Retrieves Flow interview fault records from the FlowRecordRelation and FlowInterview objects. Shows flows that have errored in runtime with their fault message and the record that triggered the error. flowApiName: filter to a specific flow API name (optional — returns errors for all flows if omitted) lookbackHours: how many hours back to search (default: 24, max: 168) limit: maximum records to return (default: 50) Returns: flow name, start time, error message, and related record ID for each fault. It is categorised as a Read tool in the Salesforce Metadata Mcp MCP Server, which means it retrieves data without modifying state.
Register the Salesforce Metadata MCP server in PolicyLayer and add a rule for sf_get_flow_errors: 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 Metadata Mcp. Nothing to install.
sf_get_flow_errors 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 sf_get_flow_errors 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_get_flow_errors. 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_get_flow_errors is provided by the Salesforce Metadata MCP server (salesforce-metadata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Salesforce Metadata, and thousands of servers like it.
This server
Across the catalogue