Search transactions using natural language queries.
AI agents call semantic_search_transactions to retrieve information from Marqeta DiVA API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it queries and retrieves transaction data without side effects. Severity is elevated to 'medium' rather than 'low' because unrestricted access to financial transaction data could enable information disclosure about customer spending patterns, account activities, and potentially sensitive payment details if the semantic search lacks proper access controls or filtering.
From the tool's definition Tool name 'semantic_search_transactions' and description 'Search transactions using natural language queries' indicate retrieval of transaction data.
Attacks that exploit this kind of access
Search transactions using natural language queries. It is categorised as a Read tool in the Marqeta DiVA API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Marqeta DiVA API MCP Server MCP server in PolicyLayer and add a rule for semantic_search_transactions: 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 Marqeta DiVA API MCP Server. Nothing to install.
semantic_search_transactions 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_transactions 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_transactions. 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_transactions is provided by the Marqeta DiVA API MCP Server MCP server (zvika-finally/marqeta-diva-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 →