Scan a codebase from a project with a selection of rules. Evaluates rules against specified files and outputs results. When invoked without specifying any rules, all rules are run by default. If any of the input parameters were not provided, then you choose them based on the target file or files.
AI agents invoke scanner_run to trigger actions in Salesforce CLI MCP Server. 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 scanner_run tool executes rule evaluations against files—a programmatic operation whose effects depend on which rules run and what they check for. This is Execute rather than Read because scanning engines often have side effects (logging, reporting, potential rule-triggered actions).
From the tool's definition Tool performs scanning and rule evaluation against codebase files ('Evaluates rules against specified files'), which involves executing external scanning logic/operations.
Attacks that exploit this kind of access
Scan a codebase from a project with a selection of rules. Evaluates rules against specified files and outputs results. When invoked without specifying any rules, all rules are run by default. If any of the input parameters were not provided, then you choose them based on the target file or files. It is categorised as a Execute tool in the Salesforce CLI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Salesforce CLI MCP Server MCP server in PolicyLayer and add a rule for scanner_run: 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 CLI MCP Server. Nothing to install.
scanner_run 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 scanner_run 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 scanner_run. 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.
scanner_run is provided by the Salesforce CLI MCP Server MCP server (perrynet/salesforce-cli-mcp-server). 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 →