Preview a Sanka-native merge plan for duplicate companies or contacts. Use after query_records mode=
AI agents call preview_record_merge 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.
The tool generates a preview of what a merge would look like for duplicate records. It does not actually perform the merge, only displays the plan. This is a read-only operation similar to a dry-run or simulation. Severity is low since it only retrieves/displays information without side effects.
From the tool's definition 'Preview a Sanka-native merge plan' — this tool previews/shows a merge plan without executing it, functioning as a read/query operation.
Attacks that exploit this kind of access
Preview a Sanka-native merge plan for duplicate companies or contacts. Use after query_records mode=. 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 preview_record_merge: 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.
preview_record_merge 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 preview_record_merge 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 preview_record_merge. 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.
preview_record_merge 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 →