AI agents call semantic_search to retrieve information from MCP RSS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only search function that retrieves and queries data from RSS feeds without causing side effects, modifications, or irreversible changes. The use of AI embeddings does not elevate it beyond Read category since the tool itself does not execute arbitrary code or make changes to data—it only searches existing articles and returns results.
From the tool's definition Tool performs 'semantic search' to 'find conceptually similar articles' using 'vector embeddings'. The description indicates query and retrieval operations with no mention of modifications, deletions, or external executions.
Attacks that exploit this kind of access
AI-powered semantic search using vector embeddings (OpenAI text-embedding-3-small). Finds conceptually similar articles without exact keyword matches. Use for: natural language queries (e.g.,. It is categorised as a Read tool in the MCP RSS MCP Server, which means it retrieves data without modifying state.
Register the MCP RSS MCP server in PolicyLayer and add a rule for semantic_search: 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 MCP RSS. Nothing to install.
semantic_search 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 semantic_search 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 semantic_search. 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.
semantic_search is provided by the MCP RSS MCP server (ronnycoding/my_mcp_rss). 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 →