The MULTI-CHAIN keyless RPC for agents - delete the API key. POST a standard JSON-RPC request (single or batch up to 10) of READ-ONLY methods (eth_call, eth_getBalance, eth_getCode, eth_getLogs, eth_blockNumber, eth_getTransactionReceipt, etc.). Reads BOTH Base (default) AND Ethereum mainnet - ad...
Part of the LION - keyless data for AI agents: CPG, enrichment, social (attested) server.
Free to start. No card required.
AI agents may call lion_keyless_base_rpc to permanently remove or destroy resources in LION - keyless data for AI agents: CPG, enrichment, social (attested). Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call lion_keyless_base_rpc in a loop, permanently destroying resources in LION - keyless data for AI agents: CPG, enrichment, social (attested). There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"lion_keyless_base_rpc"
]
}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_keyless_base_rpc gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
The MULTI-CHAIN keyless RPC for agents - delete the API key. POST a standard JSON-RPC request (single or batch up to 10) of READ-ONLY methods (eth_call, eth_getBalance, eth_getCode, eth_getLogs, eth_blockNumber, eth_getTransactionReceipt, etc.). Reads BOTH Base (default) AND Ethereum mainnet - add chain=ethereum (query string ?chain=ethereum) to read Ethereum (eip155:1). LION forwards across a free public RPC failover set for that chain and returns the JSON-RPC reply, plus decoded_events (labeled ERC-20/721 Transfer/Approval) for any eth_getLogs. No API key, no signup, no node. Read-only; write methods rejected before payment. GRANULAR per-method pricing (matches/beats granular incumbents like OneSource): eth_blockNumber/eth_chainId $0.001; eth_getBalance/eth_getCode/eth_getTransactionCount $0.002; eth_call/eth_getTransactionReceipt $0.003; eth_getLogs $0.005; batch = sum of its methods. Broader than an Ethereum-only keyless RPC. Payment is always USDC on Base. Pay-per-call via x402, or prepay once (lion_credits_purchase) and call with Authorization: Bearer lct_... with no new signing. [x402 paid tool: GET /api/x402/keyless-base-rpc-json?src=mcp returns the 402 challenge with the canonical payTo; price 0.001 USDC on Base eip155:8453.]. It is categorised as a Destructive tool in the LION - keyless data for AI agents: CPG, enrichment, social (attested) MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the LION - keyless data for AI agents: CPG, enrichment, social (attested) MCP server in PolicyLayer and add a rule for lion_keyless_base_rpc: 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_keyless_base_rpc is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the lion_keyless_base_rpc 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_keyless_base_rpc. 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_keyless_base_rpc 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.