AI agents call madeonsol_stream_token to retrieve information from Madeonsol without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool generates an authentication token for WebSocket streaming access. It creates a credential/token (which is a Write-adjacent action), but the primary purpose is to enable read-only data streaming (market data, KOL activity). The token itself grants read access to streaming data and does not move funds, execute trades, or modify persistent data.
From the tool's definition Generate a 24h WebSocket streaming token... ws_url for KOL/deployer streaming... dex_ws_url for all-DEX trade streaming
Attacks that exploit this kind of access
Generate a 24h WebSocket streaming token. Includes ws_url for KOL/deployer streaming (Pro/Ultra) and dex_ws_url for all-DEX trade streaming (Ultra only). It is categorised as a Read tool in the Madeonsol MCP Server, which means it retrieves data without modifying state.
Register the Madeonsol MCP server in PolicyLayer and add a rule for madeonsol_stream_token: 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 Madeonsol. Nothing to install.
madeonsol_stream_token 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 madeonsol_stream_token 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 madeonsol_stream_token. 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.
madeonsol_stream_token is provided by the Madeonsol MCP server (mcp-server-madeonsol). 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 →