Search within a data source view
AI agents call search_data_source_view to retrieve information from Dust MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search query within a data source view, which is a retrieval operation with no side effects. It does not create, modify, delete, or execute code. The blast radius of misuse is limited to unauthorized information disclosure, making it a low-severity read operation.
From the tool's definition Tool name 'search_data_source_view' and description 'Search within a data source view' indicate a query operation that retrieves data without modification. The verb 'search' is a classic read operation.
Attacks that exploit this kind of access
Search within a data source view. It is categorised as a Read tool in the Dust MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Dust MCP Server MCP server in PolicyLayer and add a rule for search_data_source_view: 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 Dust MCP Server. Nothing to install.
search_data_source_view 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 search_data_source_view 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 search_data_source_view. 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.
search_data_source_view is provided by the Dust MCP Server MCP server (ma3u/dust-mcp-server-postman-railway). 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 →