Limitguard publishes machine-readable discovery files for three AI agent protocols. All discovery endpoints are free and require no authentication.
Discovery Endpoints
All /.well-known/* requests bypass x402 payment middleware completely — no payment or API key needed.
x402 Bazaar Listing
Enables AI agents to discover available endpoints and their payment requirements automatically.
The full response lists all 18 priced endpoints — including the 5 MCP tool endpoints and the 4 API-key tier-upgrade endpoints (29–999). See Pricing for the complete, current table.
Also available at /v1/sales/listing for the same data.
A2A Agent Card
Google’s Agent-to-Agent (A2A) protocol for agent capability discovery.
Returns capabilities, skills, and how to invoke Limitguard as an A2A agent. Other agents can discover what Limitguard can do and how to interact with it programmatically.
MCP Manifest
Model Context Protocol tools for LLM agents (Claude, GPT-4, etc.).
Returns tool definitions that LLM agents can use to call Limitguard endpoints as native tools. See the AI Agent Integration guide for usage examples.
llms.txt
Standard machine-readable format for LLM consumption.
Cross-Sell Recommendations
AI agents calling one endpoint can discover complementary services:
Needs an API key (a free or sandbox key works). Returns the complementary endpoints for the one you name, with their prices; for /v1/risk/score that is the full /v1/entity/check.
Integration Example
An AI agent discovering and using Limitguard autonomously: