AgentAPI: AI-Ready API Directory for Openclaw

AgentAPI is a curated, machine-readable directory of APIs specifically designed for AI agents, featuring native MCP compatibility and x402 crypto-billing.

gizmo-dev
v1.0.0
Feb 19, 2026
0
1.9k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install agentapi-hub

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install agentapi-hub using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is AgentAPI: AI-Ready API Directory?

AgentAPI serves as a central hub for developers building agentic workflows within the Openclaw Skills framework. It provides a curated database of APIs that are not just human-readable, but optimized for machine consumption. By focusing on MCP-compatible integrations and innovative payment protocols, it simplifies the way AI agents discover and interact with external services. This skill allows agents to search for tools across categories like search, AI inference, communication, and databases.

One of the standout features of this tool within the Openclaw Skills ecosystem is the support for x402, a pay-per-use protocol using USDC on the Base chain. This eliminates the need for manual API key management and subscriptions, allowing agents to self-provision access to premium tools programmatically and autonomously.

AgentAPI: AI-Ready API Directory Use Cases

  • Finding MCP-compatible search engines like Brave or Tavily for RAG workflows.
  • Discovering high-speed LLM inference providers like Groq or Gemini.
  • Integrating communication tools such as Resend or Twilio into agentic tasks.
  • Utilizing x402 billing to allow agents to pay for their own API usage without human intervention.
  • Locating vector databases and storage solutions for persistent agent memory.

How AgentAPI: AI-Ready API Directory Works

  1. The agent queries the AgentAPI directory using specific keywords or category filters.
  2. The system returns machine-readable JSON data containing documentation, authentication methods, and MCP compatibility status.
  3. For x402-enabled endpoints, the agent attempts a request and receives a 402 Payment Required status.
  4. The agent processes a USDC payment on the Base chain to the specified recipient address provided in the response.
  5. The request is retried with the payment proof in the header, and the service returns the requested data.

AgentAPI: AI-Ready API Directory Setup

To integrate this directory into your project, you can access the AgentAPI via standard HTTP requests. This makes it easy to incorporate into any Openclaw Skills configuration.

# Search for email APIs that are MCP compatible
curl "https://agentapihub.com/api/v1/apis?q=email&mcp=true"

# Fetch all AI category APIs for model inference
curl "https://agentapihub.com/api/v1/apis?category=ai"

AgentAPI: AI-Ready API Directory Data Schema & Taxonomy

The skill provides a structured JSON response for every API in its database, ensuring compatibility with Openclaw Skills data processing.

Field Description
id Unique identifier for the API provider
name Display name of the service
category Functional group (e.g., communication, search, database)
auth Required authentication type (api_key, x402, or freemium)
mcpCompatible Boolean indicating Model Context Protocol support
examplePrompt Suggested natural language prompt for the agent to use the tool
pricingDetails Human-readable breakdown of costs and free tiers

AgentAPI: AI-Ready API Directory Advanced Features

  • Native x402 payment protocol support for crypto-native autonomous agents using USDC on Base.
  • Full MCP compatibility across 50+ curated API services for seamless IDE integration.
  • Real-time search and filtering by capability, latency, and reliability metrics.
  • Machine-readable documentation endpoints designed for direct LLM ingestion and tool-calling.
  • Support for high-speed inference providers like Groq for low-latency Openclaw Skills responses.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*