Get the most recently created tokens on pump.fun. Useful for discovering new launches.
AI agents call getNewTokens to retrieve information from Pump Fun MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries historical token data from pump.fun without creating, modifying, deleting, or executing any operations. It is a passive read operation with no blast radius if misused by an AI agent—the worst outcome is fetching unwanted data.
From the tool's definition Tool name 'getNewTokens' and description 'Get the most recently created tokens on pump.fun' indicate a retrieval operation with no side effects. The verb 'Get' and use case 'discovering new launches' confirm data querying without modification or execution.
Documented attack patterns abuse exactly the kind of access getNewTokens gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pump Fun MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for getNewTokens:
{
"version": "1",
"default": "deny",
"tools": {
"getNewTokens": {}
}
} getNewTokens is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the most recently created tokens on pump.fun. Useful for discovering new launches. It is categorised as a Read tool in the Pump Fun MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Pump Fun MCP Server MCP server in PolicyLayer and add a rule for getNewTokens: 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 Pump Fun MCP Server. Nothing to install.
getNewTokens 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 getNewTokens 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 getNewTokens. 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.
getNewTokens is provided by the Pump Fun MCP Server MCP server (nirholas/pump-fun-workers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pump Fun MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Pump Fun MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.