home / skills / openclaw / skills / agentapi-hub

agentapi-hub skill

/skills/gizmo-dev/agentapi-hub

This skill helps you explore the AgentAPI directory of MCP-compatible APIs, enabling fast discovery and usage with x402 pay-per-use billing.

npx playbooks add skill openclaw/skills --skill agentapi-hub

Review the files below or copy the command above to add this skill to your agents.

Files (2)
SKILL.md
4.9 KB
---
name: agentapi
description: Browse and search the AgentAPI directory - a curated database of APIs designed for AI agents. Find MCP-compatible APIs for search, AI, communication, databases, payments, and more. Includes x402 pay-per-use billing with USDC on Base.
author: gizmolab
version: 1.0.3
tags: [api, mcp, agents, directory, search, integrations, x402, crypto, payments]
---

# AgentAPI

A curated directory of APIs designed for AI agents. Machine-readable. MCP-compatible. Agent-accessible.

**Website:** https://agentapihub.com  
**Billing API:** https://api.agentapihub.com  
**Docs:** https://api.agentapihub.com/api/docs

## x402 Pay-Per-Use Billing

AgentAPI supports **x402** — a payment protocol that lets AI agents pay for API calls with USDC on Base. No API keys required.

### How It Works

1. Agent calls API endpoint (e.g., `/api/gemini/chat/completions`)
2. Server returns `402 Payment Required` with price + wallet address
3. Agent sends USDC payment on Base chain
4. Agent retries with payment proof in header
5. Server verifies payment, proxies request, returns response

### Example Flow

```bash
# 1. Initial request returns 402
curl https://api.agentapihub.com/api/gemini/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-2.0-flash","messages":[{"role":"user","content":"Hello"}]}'

# Response: 402 Payment Required
# {
#   "price": "0.001",
#   "currency": "USDC",
#   "chain": "base",
#   "recipient": "0xcCb92A101347406ed140b18C4Ed27276844CD9D7",
#   "paymentId": "pay_abc123"
# }

# 2. Agent pays on Base, retries with proof
curl https://api.agentapihub.com/api/gemini/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-Payment-Proof: 0x..." \
  -d '{"model":"gemini-2.0-flash","messages":[{"role":"user","content":"Hello"}]}'
```

### Available x402 APIs

| API | Endpoint | Price |
|-----|----------|-------|
| Gemini Chat | `/api/gemini/chat/completions` | ~$0.001/req |
| Gemini Embeddings | `/api/gemini/embeddings` | ~$0.0005/req |

### Why x402?

- **No API keys** — Agents self-provision access
- **Pay-per-use** — No subscriptions, no minimums
- **Crypto-native** — USDC on Base (fast, cheap txns)
- **Agent-friendly** — Programmatic payments without human bottleneck

## Quick Search

### By Category

| Category | APIs | Example |
|----------|------|---------|
| Search | Brave, Serper, Exa, Tavily, Perplexity | Web search with AI summaries |
| AI & ML | OpenAI, Claude, Gemini, Groq, Replicate | LLM inference, image gen |
| Communication | Resend, Twilio, Slack, Discord, Telegram | Email, SMS, messaging |
| Database | Supabase, Pinecone, Qdrant, Neon, Upstash | SQL, vectors, KV store |
| Payments | Stripe, Lemon Squeezy, PayPal | Payment processing |
| Scraping | Firecrawl, Browserbase, Apify | Web scraping, automation |
| Developer | GitHub, Vercel, Linear, Sentry | Code, deploy, issues |
| Productivity | Notion, Google Calendar, Todoist | Tasks, scheduling |

### MCP-Compatible APIs

All 50+ APIs in the directory are MCP-compatible. Filter with `?mcp=true`.

## API Access

### JSON Endpoint

```bash
# Fetch all APIs
curl https://agentapihub.com/api/v1/apis

# Search by capability
curl "https://agentapihub.com/api/v1/apis?q=send+email&mcp=true"

# Filter by category
curl "https://agentapihub.com/api/v1/apis?category=ai"
```

### Response Format

```json
{
  "id": "resend",
  "name": "Resend",
  "description": "Modern email API for developers",
  "category": "communication",
  "provider": "Resend",
  "docs": "https://resend.com/docs",
  "auth": "api_key",
  "pricing": "freemium",
  "pricingDetails": "3,000 free/mo, then $20/mo",
  "rateLimit": "10 req/sec",
  "mcpCompatible": true,
  "examplePrompt": "Send an email notification using Resend",
  "latency": "fast",
  "reliability": 99.9,
  "tags": ["email", "transactional", "notifications"]
}
```

## Top APIs by Category

### Search
- **Brave Search** - Privacy-focused, 2k free/mo
- **Exa** - Neural/semantic search for AI
- **Tavily** - Built specifically for AI agents

### AI & ML
- **OpenAI** - GPT-4, DALL-E, Whisper
- **Anthropic Claude** - Best for reasoning/coding
- **Groq** - Fastest inference (500+ tok/sec)

### Communication
- **Resend** - Simple email API, 3k free/mo
- **Twilio** - SMS/voice, industry standard
- **Slack/Discord/Telegram** - Team messaging

### Database
- **Supabase** - Postgres + auth + storage
- **Pinecone/Qdrant** - Vector DBs for RAG
- **Upstash** - Serverless Redis

## Usage Examples

```markdown
# Find an API for sending emails
Search AgentAPI for "email" → Returns Resend, SendGrid, Twilio

# Find vector databases for RAG
Search AgentAPI for "vector embeddings" → Returns Pinecone, Qdrant, Weaviate

# Find fast LLM inference
Search AgentAPI for category "ai" + filter by latency → Returns Groq, Gemini Flash
```

## Contributing

Submit new APIs at https://agentapihub.com (Submit API link in footer).

## Built By

GizmoLab ([@gizmolab_](https://twitter.com/gizmolab_)) — [gizmolab.io](https://gizmolab.io)

Overview

This skill lets you browse and search the AgentAPI directory — a curated, machine-readable catalog of APIs built for AI agents. I maintain a searchable index of MCP-compatible APIs across categories like search, AI, communication, databases, payments, and scraping. It also exposes x402 pay-per-use billing with USDC on Base, so agents can programmatically pay for API calls without API keys.

How this skill works

You query the JSON endpoints to list or filter APIs by category, capability, latency, or MCP compatibility. For x402-enabled endpoints the server returns a 402 with price and recipient; the agent pays USDC on Base and retries with payment proof in a header. Responses include structured metadata (id, name, category, auth, pricing, docs, tags) so agents can automatically select and integrate the right API.

When to use it

  • Discover MCP-compatible APIs for autonomous agents and workflows
  • Find pay-per-use AI endpoints that accept programmatic USDC payments on Base
  • Filter and compare APIs by category, latency, pricing model, and tags
  • Automate API selection for RAG, search, messaging, or payments within an agent
  • Archive or audit available API versions and metadata for compliance

Best practices

  • Filter results with query parameters (q, category, mcp=true) to narrow candidates quickly
  • Use the structured response fields (auth, pricing, rateLimit) to automate credential and cost handling
  • For x402 endpoints, implement robust payment proof handling and retry logic after 402 responses
  • Cache metadata for performance but refresh periodically to keep pricing and availability up to date
  • Respect rate limits and tag-based capabilities when composing multi-API agent pipelines

Example use cases

  • Agent selects a vector DB and embedding provider for a RAG pipeline by filtering category=database and tags=embeddings
  • Autonomous agent discovers a short-latency LLM (Groq or Gemini Flash) and calls it via x402 with on-chain payment
  • Tooling lists communication APIs (Resend, Twilio) and auto-generates integration snippets with provider docs
  • DevOps bot audits the directory to ensure all MCP-compatible APIs used by an app remain available

FAQ

Do I need API keys to use x402 endpoints?

No. x402 endpoints use pay-per-use USDC payments on Base so agents can self-provision without traditional API keys.

How do I filter for MCP-compatible APIs?

Add the query parameter mcp=true to list only MCP-compatible APIs in search requests.