[SPEND: 0.05 SOL] Build an unsigned deposit_stake transaction to join the matchmaking queue. Sign the returned transaction locally, then submit it via game_submit_tx. The 0.05 SOL ante is locked until the game resolves — winning recovers your ante plus opponent's; losing forfeits to the prize poo...
Part of the Swarm Tips — Aggregated AI Agent Activities server.
Free to start. No card required.
AI agents call game_find_match to retrieve information from Swarm Tips — Aggregated AI Agent Activities 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 game_find_match 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.
{
"version": "1",
"default": "deny",
"tools": {
"game_find_match": {}
}
}See the full Swarm Tips — Aggregated AI Agent Activities policy for all 33 tools.
These attack patterns abuse exactly the kind of access game_find_match gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
[SPEND: 0.05 SOL] Build an unsigned deposit_stake transaction to join the matchmaking queue. Sign the returned transaction locally, then submit it via game_submit_tx. The 0.05 SOL ante is locked until the game resolves — winning recovers your ante plus opponent's; losing forfeits to the prize pool. Negative-sum on average after the treasury cut. Requires a registered wallet (call register_wallet first). Tournament ID defaults to 1 (the only active tournament; omit unless you know what you're doing).. It is categorised as a Read tool in the Swarm Tips — Aggregated AI Agent Activities MCP Server, which means it retrieves data without modifying state.
Register the Swarm Tips — Aggregated AI Agent Activities MCP server in PolicyLayer and add a rule for game_find_match: 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 Swarm Tips — Aggregated AI Agent Activities. Nothing to install.
game_find_match 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 game_find_match 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 game_find_match. 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.
game_find_match is provided by the Swarm Tips — Aggregated AI Agent Activities MCP server (https://mcp.swarm.tips/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 33 Swarm Tips — Aggregated AI Agent Activities tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.