The repeat-usage killer feature. ONE x402 payment buys a "lct_..." session token with balance ($0.10 / $0.50 / $1.00 packs). Then call ANY LION paid tool with "Authorization: Bearer lct_..." - balance deducts automatically. No new EIP-712, no 402, no JWS per call until empty. Top up anytime with ...
Part of the LION - keyless data for AI agents: CPG, enrichment, social (attested) server.
Free to start. No card required.
AI agents call lion_credits_purchase to retrieve information from LION - keyless data for AI agents: CPG, enrichment, social (attested) 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 lion_credits_purchase 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": {
"lion_credits_purchase": {}
}
}See the full LION - keyless data for AI agents: CPG, enrichment, social (attested) policy for all 20 tools.
These attack patterns abuse exactly the kind of access lion_credits_purchase 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.
The repeat-usage killer feature. ONE x402 payment buys a "lct_..." session token with balance ($0.10 / $0.50 / $1.00 packs). Then call ANY LION paid tool with "Authorization: Bearer lct_..." - balance deducts automatically. No new EIP-712, no 402, no JWS per call until empty. Top up anytime with another single purchase. Essential for agents doing 50+ calls/day. Same error_recovery and payment_instructions as other tools. Keyless, no PII, USDC on Base. [x402 paid tool: GET /api/x402/credits-purchase-json?src=mcp returns the 402 challenge with the canonical payTo; price 0.10 USDC on Base eip155:8453.]. It is categorised as a Read tool in the LION - keyless data for AI agents: CPG, enrichment, social (attested) MCP Server, which means it retrieves data without modifying state.
Register the LION - keyless data for AI agents: CPG, enrichment, social (attested) MCP server in PolicyLayer and add a rule for lion_credits_purchase: 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 LION - keyless data for AI agents: CPG, enrichment, social (attested). Nothing to install.
lion_credits_purchase 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 lion_credits_purchase 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 lion_credits_purchase. 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.
lion_credits_purchase is provided by the LION - keyless data for AI agents: CPG, enrichment, social (attested) MCP server (https://lionx402.com/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 20 LION - keyless data for AI agents: CPG, enrichment, social (attested) 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.