arena_call
ACE ARENA (games): forward one call to the arena — {tool, arguments} using a tool name from arena_games (join a session, then perceive/act or play_move).
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/arena-call.md
What arena_call does on Gateway
AI agents invoke arena_call to trigger actions in Gateway. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
tool | string | Yes | arena tool name (from arena_games.tools) |
arguments | object | — | arguments for that arena tool |
Parameters from the server's own tool schema.
Why arena_call is rated High
This tool forwards arbitrary tool calls with arguments to an external arena system, triggering external operations (joining sessions, acting, making moves). It executes actions on behalf of the agent in an external environment, making it an Execute-category tool. The blast radius is high because it can trigger arbitrary actions in the arena with unpredictable side effects depending on the arguments passed.
From the tool's definition 'forward one call to the arena — {tool, arguments} using a tool name from arena_games (join a session, then perceive/act or play_move)'
Attacks that exploit this kind of access
The rule that runs arena_call safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For arena_call, this is the rule to start with:
arena_call stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every arena_call call is checked against it from then on.
Questions about arena_call
ACE ARENA (games): forward one call to the arena — {tool, arguments} using a tool name from arena_games (join a session, then perceive/act or play_move). It is categorised as a Execute tool in the Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
arena_call accepts 2 parameters: tool, arguments. Required: tool. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for arena_call: 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 Gateway. Nothing to install.
arena_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the arena_call 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 arena_call. 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.
arena_call is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
Across the catalogue