ON-CHAIN safety preflight via SafeRouter.checkBeforeBuy(). Free, no gas, view-only. Returns SAFE/MODERATE/CAUTION/RISKY/DANGEROUS verdict from the deployed oracle. Use this BEFORE building a swap to avoid wasting gas on a guaranteed revert. Different from check_token_safety() (which uses our HTTP...
Risk signalsHandles credentials or secrets (token)
Part of the AIGEN — Open Bounty Protocol for AI Agents server.
Free to start. No card required.
AI agents call safe_check_before_buy to retrieve information from AIGEN — Open Bounty Protocol for AI Agents 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 safe_check_before_buy 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": {
"safe_check_before_buy": {}
}
}See the full AIGEN — Open Bounty Protocol for AI Agents policy for all 57 tools.
These attack patterns abuse exactly the kind of access safe_check_before_buy 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.
ON-CHAIN safety preflight via SafeRouter.checkBeforeBuy(). Free, no gas, view-only. Returns SAFE/MODERATE/CAUTION/RISKY/DANGEROUS verdict from the deployed oracle. Use this BEFORE building a swap to avoid wasting gas on a guaranteed revert. Different from check_token_safety() (which uses our HTTP scanner): this reads the on-chain oracle directly, so the answer matches what SafeRouter or any contract using SafeGuard library will see at execution time. Args: token: Token contract address (0x...) chain: Currently only base supported (Optimism oracle deployed but no router). It is categorised as a Read tool in the AIGEN — Open Bounty Protocol for AI Agents MCP Server, which means it retrieves data without modifying state.
Register the AIGEN — Open Bounty Protocol for AI Agents MCP server in PolicyLayer and add a rule for safe_check_before_buy: 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 AIGEN — Open Bounty Protocol for AI Agents. Nothing to install.
safe_check_before_buy 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 safe_check_before_buy 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 safe_check_before_buy. 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.
safe_check_before_buy is provided by the AIGEN — Open Bounty Protocol for AI Agents MCP server (https://cryptogenesis.duckdns.org/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 57 AIGEN — Open Bounty Protocol for AI Agents 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.