AI agents call get_recent_signatures to retrieve information from Onchain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves transaction metadata (signatures) from the blockchain without modifying, executing operations, or creating side effects. It is a pure query operation that returns historical information about an account's transaction activity. The blast radius of misuse is minimal—at worst, an AI could map account activity patterns, but cannot move funds, execute code, or alter state.
From the tool's definition Tool name is 'get_recent_signatures' and description states 'List the most recent transaction signatures touching an account.' The verb 'List' and the read-only nature of retrieving historical transaction signatures indicate data retrieval with no side…
Attacks that exploit this kind of access
List the most recent transaction signatures touching an account. It is categorised as a Read tool in the Onchain MCP Server, which means it retrieves data without modifying state.
Register the Onchain MCP server in PolicyLayer and add a rule for get_recent_signatures: 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 Onchain. Nothing to install.
get_recent_signatures 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_recent_signatures 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_recent_signatures. 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_recent_signatures is provided by the Onchain MCP server (sylvainlondon136/onchain-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 →