Resolve an ambiguous user phrase such as a company, deal, or Salesforce Opportunity reference into candidate records before previewing or starting a workflow.
AI agents call resolve_record to retrieve information from Sanka MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool resolves/looks up records matching a user phrase — it retrieves candidate records for review without creating, modifying, or deleting anything. It is a read/search operation used as a precursor to other actions.
From the tool's definition Resolve an ambiguous user phrase... into candidate records before previewing or starting a workflow
Attacks that exploit this kind of access
Resolve an ambiguous user phrase such as a company, deal, or Salesforce Opportunity reference into candidate records before previewing or starting a workflow. It is categorised as a Read tool in the Sanka MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sanka MCP Server MCP server in PolicyLayer and add a rule for resolve_record: 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 Sanka MCP Server. Nothing to install.
resolve_record 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 resolve_record 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 resolve_record. 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.
resolve_record is provided by the Sanka MCP Server MCP server (sankahq/sanka-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 →