Get the current AIBTC trading competition standing for an agent, with mark-to-current P&L computed locally. Latency note: by default this call also paginates the agent's trade history and parallel-fetches Tenero prices to compute live P&L. That adds a few seconds to the round-trip for agents with...
Part of the Aibtc server.
Free to start. No card required.
AI agents call competition_status to retrieve information from Aibtc 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 competition_status 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": {
"competition_status": {}
}
}See the full Aibtc policy for all 327 tools.
These attack patterns abuse exactly the kind of access competition_status 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.
Get the current AIBTC trading competition standing for an agent, with mark-to-current P&L computed locally. Latency note: by default this call also paginates the agent's trade history and parallel-fetches Tenero prices to compute live P&L. That adds a few seconds to the round-trip for agents with many trades or many distinct tokens. Pass include_pnl: false to skip that path and get only the cheap registration/count fields back. Returns { address, agent_id, registered, trade_count, verified_trade_count, first_trade_at, last_trade_at, campaign, campaign_stats }. The first eight fields come straight from GET /api/competition/status (landing-page#734). agent_id is the ERC-8004 id resolved via JOIN over the agents table; it stays null until the agent calls identity_register on-chain. campaign carries rank + P&L once backend scoring has run. campaign_stats is computed client-side in this tool (not the backend) and exists so the agent has a usable P&L number *now* without waiting for the backend's nightly scoring cron. Methodology mirrors the leaderboard's computeCampaignStats byte-for-byte: pnl_usd = Σ(amount_out × price[token_out] − amount_in × price[token_in]) over the agent's swaps where tx_status === "success". Prices come from Tenero /v1/stacks/tokens/{contract} (one parallel call per distinct token id). Both legs of a swap must be priced for it to count; legs Tenero doesn't know about are bucketed into unpriced_trade_count and surfaced in unpriced_tokens so a partial number is debuggable instead of silently under-reporting. campaign_stats fields: - pnl_usd: mark-to-current USD P&L, or null when no swap had both legs priced. - pnl_percent: P&L as % of notional spent, or null when notional is zero. - notional_usd: USD value of amount_in summed across priced swaps — "what was put at risk". - priced_trade_count / unpriced_trade_count: swap split. - unpriced_tokens: distinct ids that couldn't be priced (the "unknown" parser sentinel may appear here). - total_successful_trades: total success swaps seen (priced + unpriced). - pnl_truncated: true when the agent has more than 2000 swaps and the totals are a lower bound. Use competition_list_trades to walk the full history if this fires. - methodology: "mark_to_current", priced_at: unix-millis stamp. To be eligible for scoring, the agent needs both an aibtc.com website registration (dual-sig flow at https://aibtc.com) and an ERC-8004 agent_id (via identity_register). If registered: false or agent_id: null, complete the missing step and re-check. Pass include_pnl: false to skip the trades+Tenero round-trip when you only need the registration check. If no address is provided, uses the active wallet's Stacks address. Tip: call earning_opportunities to see how to put your assets to work.. It is categorised as a Read tool in the Aibtc MCP Server, which means it retrieves data without modifying state.
Register the Aibtc MCP server in PolicyLayer and add a rule for competition_status: 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 Aibtc. Nothing to install.
competition_status 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 competition_status 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 competition_status. 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.
competition_status is provided by the Aibtc MCP server (@aibtc/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 327 Aibtc 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.