Opensea

What it does

When your agent uses it

• Tasks that involve Crypto and DeFi analysis

Example prompts

• “/opensea”

Requirements

• Node.js
• A Bash shell
• A credential in OPENSEA_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Set OPENSEA_API_KEY in your environment
2. 2Preferred: Use the opensea CLI (@opensea/cli) for all queries and operations
3. 3Alternatively, use the shell scripts in scripts/ or the MCP server

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 11 files in scripts/ (Shell, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • npm
  • npx
  • openssl
  • node

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • mcp.opensea.io

  Also links to:

  • github.com
  • opensea.io

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OPENSEA_API_KEY
  • PRIVATE_KEY
  • OPENSEA_MCP_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Opensea loads about 4.7k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 35 tokens; SKILL.md has 1,435 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~35

When it runs · the whole SKILL.md, loaded when a task matches

~4.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,435 words, ~4,709 tokens.

name

opensea

description

Query NFT data, trade on the Seaport marketplace, and swap ERC20 tokens across Ethereum, Base, Arbitrum, Optimism, Polygon, and more.

export OPENSEA_API_KEY="your-api-key"

# Install the CLI globally (or use npx)
npm install -g @opensea/cli

# Get collection info
opensea collections get boredapeyachtclub

# Get floor price and volume stats
opensea collections stats boredapeyachtclub

# Get NFT details
opensea nfts get ethereum 0xbc4ca0eda7647a8ab7c2061c2e118a18a936f13d 1234

# Get best listings for a collection
opensea listings best boredapeyachtclub --limit 5

# Search across OpenSea
opensea search "cool cats"

# Get trending tokens
opensea tokens trending --limit 5

# Get a swap quote
opensea swaps quote \
  --from-chain base --from-address 0x0000000000000000000000000000000000000000 \
  --to-chain base --to-address 0xTokenAddress \
  --quantity 0.02 --address 0xYourWallet

# Install globally
npm install -g @opensea/cli

# Or use without installing
npx @opensea/cli collections get mfers

# Set via environment variable (recommended)
export OPENSEA_API_KEY="your-api-key"
opensea collections get mfers

# Or pass inline
opensea --api-key your-api-key collections get mfers

# JSON output (default)
opensea collections stats mfers

# Human-readable table
opensea --format table collections stats mfers

# Compact TOON format (best for AI agents)
opensea --format toon tokens trending --limit 5

# First page
opensea collections list --limit 5

# Pass the "next" cursor from the response to get the next page
opensea collections list --limit 5 --next "LXBrPTEwMDA..."

import { OpenSeaCLI, OpenSeaAPIError } from "@opensea/cli"

const client = new OpenSeaCLI({ apiKey: process.env.OPENSEA_API_KEY })

const collection = await client.collections.get("mfers")
const { nfts } = await client.nfts.listByCollection("mfers", { limit: 5 })
const { listings } = await client.listings.best("mfers", { limit: 10 })
const { asset_events } = await client.events.byCollection("mfers", { eventType: "sale" })
const { tokens } = await client.tokens.trending({ chains: ["base"], limit: 5 })
const results = await client.search.query("mfers", { limit: 5 })

// Swap quote
const { quote, transactions } = await client.swaps.quote({
  fromChain: "base",
  fromAddress: "0x833589fcd6edb6e08f4c7c32d4f71b54bda02913",
  toChain: "base",
  toAddress: "0x3ec2156d4c0a9cbdab4a016633b7bcf6a8d68ea2",
  quantity: "1000000",
  address: "0xYourWalletAddress",
})

// Error handling
try {
  await client.collections.get("nonexistent")
} catch (error) {
  if (error instanceof OpenSeaAPIError) {
    console.error(error.statusCode)   // e.g. 404
    console.error(error.responseBody) // raw API response
    console.error(error.path)         // request path
  }
}

opensea --format toon tokens trending --limit 3

tokens[3]{name,symbol,chain,market_cap,price_usd}:
  Ethereum,ETH,ethereum,250000000000,2100.50
  Bitcoin,BTC,bitcoin,900000000000,48000.00
  Solana,SOL,solana,30000000000,95.25
next: abc123

import { formatToon } from "@opensea/cli"

const data = await client.tokens.trending({ limit: 5 })
console.log(formatToon(data))

{
  "mcpServers": {
    "opensea": {
      "url": "https://mcp.opensea.io/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_MCP_TOKEN"
      }
    }
  }
}

mcporter call opensea.get_token_swap_quote --args '{
  "fromContractAddress": "0x0000000000000000000000000000000000000000",
  "fromChain": "base",
  "toContractAddress": "0xb695559b26bb2c9703ef1935c37aeae9526bab07",
  "toChain": "base",
  "fromQuantity": "0.02",
  "address": "0xYourWalletAddress"
}'

import { createWalletClient, http } from 'viem';
import { privateKeyToAccount } from 'viem/accounts';
import { base } from 'viem/chains';

// Extract from swap quote response
const txData = response.swap.actions[0].transactionSubmissionData;

const wallet = createWalletClient({ 
  account: privateKeyToAccount(PRIVATE_KEY), 
  chain: base, 
  transport: http() 
});

const hash = await wallet.sendTransaction({
  to: txData.to,
  data: txData.data,
  value: BigInt(txData.value)
});

mcporter call opensea.get_token_balances --args '{
  "address": "0xYourWallet",
  "chains": ["base", "ethereum"]
}'

import crypto from 'crypto';
import { privateKeyToAccount } from 'viem/accounts';

const privateKey = '0x' + crypto.randomBytes(32).toString('hex');
const account = privateKeyToAccount(privateKey);

console.log('Private Key:', privateKey);
console.log('Address:', account.address);

# Generate private key
PRIVATE_KEY="0x$(openssl rand -hex 32)"
echo "Private Key: $PRIVATE_KEY"

# Derive address (requires node + viem)
node --input-type=module -e "
import { privateKeyToAccount } from 'viem/accounts';
console.log('Address:', privateKeyToAccount('$PRIVATE_KEY').address);
"

cast wallet new

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 26 other files (scripts, references) in skills/opensea-skill of LeoYeAI/openclaw-master-skills.

• SKILL.md
• README.md
• _meta.json
• references/marketplace-api.md
• references/rest-api.md
• references/seaport.md
• references/stream-api.md
• references/token-swaps.md
• scripts/opensea-account-nfts.sh
• scripts/opensea-best-listing.sh
• scripts/opensea-best-offer.sh
• scripts/opensea-collection-nfts.sh
• scripts/opensea-collection-stats.sh
• scripts/opensea-collection.sh
• scripts/opensea-events-collection.sh
• scripts/opensea-fulfill-listing.sh
• scripts/opensea-fulfill-offer.sh
• scripts/opensea-get.sh
• scripts/opensea-listings-collection.sh
• … and 8 more

Open the folder on GitHubat commit e5199b5