THE MULTI-CHAIN KEYLESS RPC for AI agents - keyless onchain reads on BOTH Base (eip155:8453) AND Ethereum (eip155:1), no API key, in ONE call - PLUS Ed25519-attested company enrichment as a verifiable trust moat. A broader, verifiable alternative to Ethereum-only keyless RPC (e.g. OneSource). Onc...
Part of the LION - keyless data for AI agents: CPG, enrichment, social (attested) server.
Free to start. No card required.
AI agents use lion_composite_bundle to create or modify resources in LION - keyless data for AI agents: CPG, enrichment, social (attested). Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call lion_composite_bundle repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach LION - keyless data for AI agents: CPG, enrichment, social (attested).
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"lion_composite_bundle": {
"limits": [
{
"counter": "lion_composite_bundle_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}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_composite_bundle gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
THE MULTI-CHAIN KEYLESS RPC for AI agents - keyless onchain reads on BOTH Base (eip155:8453) AND Ethereum (eip155:1), no API key, in ONE call - PLUS Ed25519-attested company enrichment as a verifiable trust moat. A broader, verifiable alternative to Ethereum-only keyless RPC (e.g. OneSource). Onchain: pass address=0x... (native balance + contract flag) and/or tx=0x... (receipt: status/block/from/to); add chain=base (default) | ethereum | both. Enrichment: pass identifier=<domain|name|ticker> (+ fields or format=apollo_org) for firmographics (Wikidata CC0) + financials (SEC EDGAR), each field source-labeled + confidence-scored, the whole body Ed25519-attested (verify offline via ?verify_helper=1). Granular in-band pricing in ONE invoice: flat-rate 0.001 USDC per onchain read (per chain) + pay-per-field 0.002 USDC per enrich field (band $0.001-$0.05). Keyless x402 on Base (payment always USDC on Base); company/org-level + public onchain facts only, no PII. Prepay once (lion_credits_purchase) then call with Authorization: Bearer lct_... - no new signature. [x402 paid tool: GET /api/x402/composite-bundle-json?src=mcp returns the 402 challenge with the canonical payTo; price 0.003 USDC on Base eip155:8453.]. It is categorised as a Write tool in the LION - keyless data for AI agents: CPG, enrichment, social (attested) MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LION - keyless data for AI agents: CPG, enrichment, social (attested) MCP server in PolicyLayer and add a rule for lion_composite_bundle: 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_composite_bundle is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the lion_composite_bundle 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_composite_bundle. 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_composite_bundle 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.