AI agents call retrieve_with_sources to retrieve information from Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a semantic search query and returns results with citations. It reads and queries existing data without creating, modifying, deleting, or executing any side effects. The 'with sources' qualifier indicates enhanced metadata in the response, not a change in operation class. Semantic search is fundamentally a Read operation with no blast radius beyond information disclosure.
From the tool's definition Tool description states 'Semantic search with full citation metadata' — a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Semantic search with full citation metadata. It is categorised as a Read tool in the Rag MCP Server, which means it retrieves data without modifying state.
Register the Rag MCP server in PolicyLayer and add a rule for retrieve_with_sources: 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 Rag. Nothing to install.
retrieve_with_sources 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 retrieve_with_sources 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 retrieve_with_sources. 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.
retrieve_with_sources is provided by the Rag MCP server (mrankitvish/rag-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 →