Get all cross-chain transactions with advanced filtering and pagination.\n\nUse Cases:\n• List all transactions for a specific user\n• Find transactions by hash, chain IDs, or time range\n• Monitor transaction history with pagination\n• Filter by request status and referrer\n\nPagination: Use lim...
AI agents call relay_get_requests to retrieve information from Relay Protocol 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 as it only retrieves and queries existing transaction data across blockchains. However, severity is medium (not low) because unauthorized access to cross-chain transaction history could expose sensitive financial information about users' blockchain activities, trading patterns, and holdings across multiple networks.
From the tool's definition Tool description states "Get all cross-chain transactions" with filtering and pagination capabilities. It retrieves transaction history, user transactions, and transaction status by hash/chain/time range—all query operations with no side effects.
Attacks that exploit this kind of access
Get all cross-chain transactions with advanced filtering and pagination.\n\nUse Cases:\n• List all transactions for a specific user\n• Find transactions by hash, chain IDs, or time range\n• Monitor transaction history with pagination\n• Filter by request status and referrer\n\nPagination: Use limit (max 50) and continuation token for large result sets.\nSorting: Sort by createdAt or updatedAt in asc/desc order. It is categorised as a Read tool in the Relay Protocol MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Relay Protocol MCP Server MCP server in PolicyLayer and add a rule for relay_get_requests: 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 Relay Protocol MCP Server. Nothing to install.
relay_get_requests 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 relay_get_requests 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 relay_get_requests. 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.
relay_get_requests is provided by the Relay Protocol MCP Server MCP server (warengonzaga/relay-protocol-mcp-server). 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 →