AI agents call get-transactions to retrieve information from Mcp Otc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical transaction data from a blockchain without modifying, deleting, or executing any operations. It is a pure query operation analogous to a database SELECT statement. The sibling tools (check-balance, get-contract-abi, get-ens-name, get-gas-prices, get-token-transfers) are all Read operations, consistent with this being an Etherscan-like explorer server.
From the tool's definition Tool name 'get-transactions' and description 'Get recent transactions for an Ethereum address' indicate data retrieval only. The verb 'Get' and context of querying blockchain transaction history for a given address show no side effects or state modification.
Attacks that exploit this kind of access
Get recent transactions for an Ethereum address. It is categorised as a Read tool in the Mcp Otc MCP Server, which means it retrieves data without modifying state.
Register the Mcp Otc MCP server in PolicyLayer and add a rule for get-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 Mcp Otc. Nothing to install.
get-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 get-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 get-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.
get-transactions is provided by the Mcp Otc MCP server (otc-ai/mcp-otc). 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 →