🚀 Interactive tutorial — 5 minutes to your first API call

Getting Started

82 categories of tools. One key. 500 free credits.
Follow along step by step — from signup to production in under 5 minutes.

2-minute quickstart Full API docs
Step 1 of 6
~5 min to complete
1

Sign up & get your API key

~30 seconds

Create an account and receive your API key with 500 free credits instantly. No credit card required. You also get 8 memory APIs permanently free.

bash — CLI (recommended)
# Install the CLI
npm install -g slopshop

# You'll see:



# Sign up (interactive)
slop signup

# You'll get back:
# API Key: sk-slop-abc123...
# Balance: 500 credits
# Status: Ready to go!
bash — curl
# Sign up via the REST API
curl -X POST https://slopshop.gg/v1/auth/signup \
  -H "Content-Type: application/json" \
  -d '{"email":"you@example.com","password":"yourpassword"}'
json — response
{
  "api_key": "sk-slop-abc123def456...",
  "balance": 500,
  "message": "Welcome to slopshop.gg"
}

Save your API key — set it as an environment variable so every command picks it up automatically:

bash
# Add to ~/.zshrc or ~/.bashrc
export SLOPSHOP_KEY=sk-slop-your-key-here
🎁

Free tier includes: 500 credits on signup + 8 memory APIs always free (memory-set, memory-get, memory-search, memory-list, memory-delete, memory-stats, memory-namespace-list, counter-get). Credits never expire.

2

Make your first API call

~1 minute

Call any of the 82 categories of tools with a single POST request. Every response includes _engine: "real" to prove your data was genuinely computed.

bash
curl -X POST https://slopshop.gg/v1/crypto-hash-sha256 \
  -H "Authorization: Bearer $SLOPSHOP_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"hello slopshop"}'
python
import requests, os

r = requests.post(
    "https://slopshop.gg/v1/crypto-hash-sha256",
    headers={"Authorization": f"Bearer {os.environ['SLOPSHOP_KEY']}"},
    json={"text": "hello slopshop"}
)
print(r.json())
javascript
const res = await fetch('https://slopshop.gg/v1/crypto-hash-sha256', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.SLOPSHOP_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({ text: 'hello slopshop' })
});
console.log(await res.json());
json — response
{
  "data": {
    "hash": "a7f3c1d9e82b4f5e6c0d2a8b...",
    "algorithm": "SHA-256",
    "_engine": "real"
  },
  "meta": {
    "credits_used": 1,
    "credits_remaining": 1999
  }
}
Try it live
Runs in your browser — no API key needed
Response
💡

Every response includes _engine: "real" confirming actual computation, and credits_used so you always know the cost.

3

Use persistent memory

~1 minute

Store, retrieve, and search agent state with the free memory tier. All 8 core memory APIs cost 0 credits — always.

memory-set
→
memory-get
→
memory-search

1. Store a memory

bash
# Store agent memory (0 credits)
curl -X POST https://slopshop.gg/v1/memory-set \
  -H "Authorization: Bearer $SLOPSHOP_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "key": "user_preference",
    "value": "dark mode, timezone UTC-5",
    "namespace": "my-agent",
    "tags": "preferences,settings"
  }'

2. Retrieve it

bash
# Retrieve by key (0 credits)
curl -X POST https://slopshop.gg/v1/memory-get \
  -H "Authorization: Bearer $SLOPSHOP_KEY" \
  -H "Content-Type: application/json" \
  -d '{"key":"user_preference","namespace":"my-agent"}'

3. Search across memories

bash
# Full-text search by tag (0 credits)
curl -X POST https://slopshop.gg/v1/memory-search \
  -H "Authorization: Bearer $SLOPSHOP_KEY" \
  -H "Content-Type: application/json" \
  -d '{"namespace":"my-agent","tag":"preferences"}'
🧠

8 free memory APIs: memory-set, memory-get, memory-search, memory-list, memory-delete, memory-stats, memory-namespace-list, counter-get. Plus free semantic search via memory-vector-search. Your agent accumulates state at zero cost.

4. Upload a file to memory

Import Markdown, text, JSON, or code files directly into your agent's memory. Content is chunked and made searchable instantly.

bash — memory upload
# Import a file into memory (content is chunked + indexed)
curl -X POST https://slopshop.gg/v1/memory/upload \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content":"# My Project\n\n## Goals\nBuild the best agent backend...", "namespace":"my-project"}'

5. Python example

Use the requests library for quick integration from any Python script or agent.

python — memory operations
import requests

API = "https://slopshop.gg/v1"
KEY = "YOUR_KEY"
h = {"Authorization": f"Bearer {KEY}"}

# Store memory (free forever)
requests.post(f"{API}/memory-set", json={"key": "goal", "value": "ship v1"}, headers=h)

# Retrieve
r = requests.post(f"{API}/memory-get", json={"key": "goal"}, headers=h)
print(r.json()["data"]["value"])  # "ship v1"
4

Run an agent task

~1 minute

Describe what you want in plain English. The agent endpoint picks the right tools, chains them, executes, and returns a summarized answer.

bash — natural language agent
# Ask the agent anything — it picks the tools automatically
curl -X POST https://slopshop.gg/v1/agent/run \
  -H "Authorization: Bearer $SLOPSHOP_KEY" \
  -H "Content-Type: application/json" \
  -d '{"task": "What tech stack does stripe.com use?"}'
json — response
{
  "answer": "Stripe.com uses Cloudflare CDN, nginx, React...",
  "steps": [
    { "tool": "net-http-headers", "credits": 5 },
    { "tool": "sense-url-content", "credits": 5 }
  ],
  "total_credits": 30,
  "run_id": "run_abc123"
}

Or use the simplified /v1/ask endpoint for quick questions:

bash — simple ask
curl -X POST https://slopshop.gg/v1/ask \
  -H "Authorization: Bearer $SLOPSHOP_KEY" \
  -H "Content-Type: application/json" \
  -d '{"question": "Hash the word slopshop with SHA256"}'

📊 Pre-built templates

5 agent templates for common tasks: security-audit, content-analyzer, data-processor, domain-recon, hash-verify.

📋 Auto-history

Every agent run is logged. Retrieve past runs at GET /v1/agent/history.

⚡ SSE streaming

Add "stream": true to get real-time Server-Sent Events as the agent works.

5

Explore 82 categories of tools

~30 seconds

Browse the full catalog by category, search for what you need, or fetch the machine-readable tool list for your agent.

bash — list all tools
# Get the full tool list (JSON)
curl https://slopshop.gg/v1/tools

# Filter by category
curl https://slopshop.gg/v1/tools?category=crypto

# MCP-formatted for Claude Code
curl https://slopshop.gg/v1/tools?format=mcp

# OpenAPI spec
curl https://slopshop.gg/v1/openapi.json

📄 Browse catalog

Interactive tool browser with search, categories, and live playground.

▶ Playground

Pick any API, enter input, hit RUN. Live computation in your browser.

📚 Full docs

Complete API reference with schemas, examples, and SDK guides.

🛠 Tool directory

Filterable directory of the full catalog of tools by category and credit cost.
6

Set up MCP for Claude Code

~1 minute

Add Slopshop as an MCP server and the full catalog of tools become native Claude Code tools — no prompt engineering needed.

Option A: One-liner setup

bash
# Install the MCP server
npm install -g @slopshop/mcp

# Register with Claude Code
claude mcp add slopshop -- slopshop-mcp --key $SLOPSHOP_KEY

Option B: Manual config

json — .claude/settings.json
{
  "mcpServers": {
    "slopshop": {
      "command": "slopshop-mcp",
      "args": ["--key", "sk-slop-your-key-here"]
    }
  }
}

Once configured, Claude discovers all tools automatically via GET /v1/tools?format=mcp. Ask Claude to "hash a string" or "check SSL for a domain" and it will use Slopshop tools natively.

🤖

Works with any MCP client. While we show Claude Code here, the MCP server works with any compatible client — Cursor, Goose, Cline, OpenCode, or your own agent framework.

Universal MCP Server (v3.7.0)

The slop mcp serve command starts a local MCP server that works with Claude Desktop, Cursor, Goose, Cline, and OpenCode out of the box.

bash
# Start the universal MCP server
slop mcp serve

# Scaffold a new project with Slopshop pre-wired
slop init --full-stack my-app

See the full Ecosystem Integrations docs for Goose Recipes, Aider commands, OpenCode plugins, Cline Skills, LangChain/LangGraph adapters, and more.

7

Connect external services

~2 minutes

Connect GitHub, Slack, Linear, Notion, and other services via OAuth connectors. Configure once, and your agents can authenticate and act on your behalf. All tokens are encrypted with AES-256-GCM and auto-rotated nightly.

bash — configure a GitHub connector
# Step 7: Connect external services
curl -X POST https://slopshop.gg/v1/connectors/config \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"toolkit":"github","client_id":"YOUR_GITHUB_APP_ID","client_secret":"YOUR_SECRET","scopes":["repo"],"auth_url":"https://github.com/login/oauth/authorize","token_url":"https://github.com/login/oauth/access_token"}'

Once configured, list your connectors with GET /v1/connectors/list, start the OAuth flow with GET /v1/connectors/connect/:toolkit, or remove one with DELETE /v1/connectors/:id. You can also set up webhook triggers to fire agent workflows from external events.

🔒

Vault-secured tokens. All OAuth tokens are encrypted with AES-256-GCM and auto-rotated nightly via refresh token exchange. Revocation is immediate.

You're ready

What's next?

You've got your API key, made your first call, and know the core concepts. Here's where to go from here.

Reference

Full API docs

Every endpoint, schema, and response format for all 78 tool categories.
Pricing

Credit packs

Buy credits when you need more. Packs from $9 to enterprise.
Integrations

For AI agents

LangChain, CrewAI, Goose, Cline, Aider, OpenCode integration guides.
Compare

vs alternatives

See how Slopshop compares to RapidAPI, ApyHub, and others.