Makes a direct REST API call to Salesforce
AI agents invoke restful to trigger actions in MCP Salesforce Connector. 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.
The tool's effects are entirely argument-dependent: it could retrieve data (Read), modify records (Write), delete records (Destructive), execute Apex code (Execute), or trigger financial operations (Financial) based on which REST endpoint and payload the LLM constructs.
From the tool's definition Tool description states 'Makes a direct REST API call to Salesforce' — this is a pass-through to arbitrary Salesforce REST endpoints.
Attacks that exploit this kind of access
Makes a direct REST API call to Salesforce. It is categorised as a Execute tool in the MCP Salesforce Connector MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Salesforce Connector MCP server in PolicyLayer and add a rule for restful: 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 MCP Salesforce Connector. Nothing to install.
restful 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 restful 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 restful. 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.
restful is provided by the MCP Salesforce Connector MCP server (smn2gnt/mcp-salesforce). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.