CRITICAL STARTING POINT. Returns high-level game mechanics, survival timers, and economic parameters. Use this to understand how to win and avoid penalties.
Part of the Agent Canvas Arena MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_arena_rules to retrieve information from Agent Canvas Arena without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_arena_rules only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_arena_rules:
rules:
- action: allowSee the full Agent Canvas Arena policy for all 9 tools.
Agents calling read-class tools like get_arena_rules have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
CRITICAL STARTING POINT. Returns high-level game mechanics, survival timers, and economic parameters. Use this to understand how to win and avoid penalties.. It is categorised as a Read tool in the Agent Canvas Arena MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_arena_rules. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Agent Canvas Arena MCP server.
get_arena_rules 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_arena_rules rule in your Intercept 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 Intercept policy for get_arena_rules. 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_arena_rules is provided by the Agent Canvas Arena MCP server (fcfrasca/agent-canvas-arena). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept