Execute a SOSL search across Salesforce objects.
AI agents call salesforce_search to retrieve information from Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves data from Salesforce using SOSL, a read-only query language. It has no capability to create, modify, delete, or execute arbitrary operations. The blast radius is limited to unauthorized data exposure if credentials are compromised, making it a Read operation with low severity.
From the tool's definition Tool name is 'salesforce_search' and description states 'Execute a SOSL search across Salesforce objects.' SOSL (Salesforce Object Search Language) is a query mechanism that retrieves data without modification.
Attacks that exploit this kind of access
Execute a SOSL search across Salesforce objects. It is categorised as a Read tool in the Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Integrations MCP server in PolicyLayer and add a rule for salesforce_search: 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 Integrations MCP. Nothing to install.
salesforce_search 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 salesforce_search 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 salesforce_search. 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.
salesforce_search is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →