Returns the Alpha Arcade agent guide — data model, units, orderbook mechanics, workflows, and common pitfalls. Read this before interacting with prediction markets.
AI agents call get_agent_guide to retrieve information from Alpha Arcade without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves reference documentation and educational material about the prediction market system. It has no capability to create, modify, delete, execute commands, or move funds. It is a straightforward read operation that provides information to help agents understand the system before taking actions. Classification as Read is appropriate with high confidence.
From the tool's definition Tool name 'get_agent_guide' and description 'Returns the Alpha Arcade agent guide' indicate retrieval of informational documentation.
Documented attack patterns abuse exactly the kind of access get_agent_guide gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Alpha Arcade, and nothing reaches the server without passing your rules. This is the rule we recommend for get_agent_guide:
{
"version": "1",
"default": "deny",
"tools": {
"get_agent_guide": {}
}
}get_agent_guide 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.
Returns the Alpha Arcade agent guide — data model, units, orderbook mechanics, workflows, and common pitfalls. Read this before interacting with prediction markets. It is categorised as a Read tool in the Alpha Arcade MCP Server, which means it retrieves data without modifying state.
Register the Alpha Arcade MCP server in PolicyLayer and add a rule for get_agent_guide: 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 Alpha Arcade. Nothing to install.
get_agent_guide 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_agent_guide 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_agent_guide. 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_agent_guide is provided by the Alpha Arcade MCP server (phara23/alpha-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Alpha Arcade, 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.
20 Alpha Arcade tools catalogued and risk-classified — across an index of 43,000+ MCP servers.