Semantic search for cards in a project using OpenAI embeddings.
AI agents call search_cards_by_embedding to retrieve information from FlashCardsMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic search to retrieve flash cards from a project, matching the Read category pattern of querying data with no side effects. The severity is low because search operations have minimal blast radius—they cannot modify, delete, or expose data beyond what an authorized user can already access in the project context.
From the tool's definition Tool name 'search_cards_by_embedding' and description 'Semantic search for cards in a project' indicate a query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
Semantic search for cards in a project using OpenAI embeddings. It is categorised as a Read tool in the FlashCardsMCP MCP Server, which means it retrieves data without modifying state.
Register the FlashCards MCP server in PolicyLayer and add a rule for search_cards_by_embedding: 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 FlashCardsMCP. Nothing to install.
search_cards_by_embedding 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_cards_by_embedding 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_cards_by_embedding. 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_cards_by_embedding is provided by the FlashCards MCP server (mtib/flash-cards-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 →