Token launch bundle and sniper detection on Base. Scans first 3 blocks after launch for same-block coordinated buys. Returns risk score, bundle wallets, and dump status. Use before buying any new token to check if the launch was bundled.
AI agents call bundle_scope to retrieve information from Mcp Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
address | string | Yes |
Parameters from the server's own tool schema.
This tool retrieves and analyzes blockchain data about token launches to detect coordinated buying patterns (sniping/bundling). It is purely informational—it reads blockchain state and generates a risk assessment. While it operates in the crypto domain, it does not execute trades, move funds, modify data, or create financial commitments.
From the tool's definition Scans, returns risk score, bundle wallets, and dump status. The tool 'scans first 3 blocks after launch' and 'returns' data. It performs analysis and reporting without modifying state, executing transactions, or creating financial obligations.
Attacks that exploit this kind of access
Token launch bundle and sniper detection on Base. Scans first 3 blocks after launch for same-block coordinated buys. Returns risk score, bundle wallets, and dump status. Use before buying any new token to check if the launch was bundled. It is categorised as a Read tool in the Mcp Server MCP Server, which means it retrieves data without modifying state.
bundle_scope accepts 1 parameter: address. Required: address. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Server MCP server in PolicyLayer and add a rule for bundle_scope: 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 Server. Nothing to install.
bundle_scope 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 bundle_scope 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 bundle_scope. 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.
bundle_scope is provided by the Mcp Server MCP server (Homie4570/lso-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 →